Home

Package `RSNNS`

1. Description Get the FType definitions of the network Usage S4 method for signature SnnsR getTypeDefinitions Value a data frame containing information about FType units present in the network SnnsRObject getUnitDefinitions Get the unit definitions of the network Description Get the unit definitions of the network Usage S4 method for signature SnnsR getUnitDefinitions Value a data frame containing information about all units present in the network SnnsRObject getUnitsByName 55 SnnsRObject getUnitsByName Find all units whose name begins with a given prefix Description Find all units whose name begins with a given prefix Usage S4 method for signature SnnsR getUnitsByName prefix Arguments prefix a prefix that the names of the units to find have Value a vector with integer numbers identifying the units SnnsRObject getWeightMatrix Get the weight matrix between two sets of units Description SnnsR low level function to get the weight matrix between two sets of units Usage S4 method for signature SnnsR getWeightMatrix unitsSource unitsTarget setDimNames Arguments unitsSource a vector with numbers identifying the source units unitsTarget a vector with numbers identifying the target units setDimNames indicates whether names of units are extracted and set as row col names in the weight matrix Value the weight matrix between the t
2. Description Column wise normalization of the input matrix is reverted using the given parameters Usage denormalizeData x normParams Arguments x input data normParams the parameters generated by an earlier call to normalizeData that will be used for reverting normalization Details The input matrix is column wise denormalized using the parameters given by normParams E g if normParams contains mean and sd for every column the values are multiplied by sd and the mean is added Value column wise denormalized input See Also normalizeData getNormParameters Examples data iris values lt normalizeData iris 1 4 denormalizeData values getNormParameters values 18 dlvq dlvq Create and train a dlvq network Description Dynamic learning vector quantization DLVQ networks are similar to self organizing maps SOM som But they perform supervised learning and lack a neighborhood relationship between the prototypes Usage dlvq x Default S3 method dlvq x y initFunc DLVQ_Weights initFuncParams c 1 1 learnFunc Dynamic_LVQ learnFuncParams c 0 03 0 03 10 updateFunc Dynamic_LVQ updateFuncParams c 0 shufflePatterns TRUE Arguments x a matrix with training inputs for the network additional function parameters currently not used y the corresponding target values initFunc the initialization function to use initFuncParams the parameters for the
3. encodeClassLabels Encode a matrix of decoded class labels Description Applies analyzeClassification row wise to a matrix 22 exportToSnnsNetFile Usage encodeClassLabels x method WTA 1 h 0 Arguments x inputs method see analyzeClassification l idem h idem Value a numeric vector each number represents a different class A zero means that no class was assigned to the pattern See Also analyzeClassification Examples data iris labels lt decodeClassLabels iris 5 encodeClassLabels labels exportToSnnsNetFile Export the net to a file in the original SNNS file format Description Export the net that is present in the rsnns object in the original net SNNS file format Usage exportToSnnsNetFile object filename netname RSNNS_untitled Arguments object the rsnns object filename path and filename to be written to netname name that is given to the network in the file extractNetInfo 23 extractNetInfo Extract information from a network Description This function generates a list of data frames containing the most important information that defines a network in a format that is easy to use To get the full definition in the original SNNS format use summary rsnns or exportToSnnsNetFile instead Usage extractNetInfo object Arguments object the rsnns object Details Internally a call to SnnsRObject extractNetInfo is done and the results of this cal
4. Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German Examples Not run demo som_iris Not run demo som_cubeSnnsR data iris inputs lt normalizeData iris 1 4 norm model lt som inputs mapX 16 mapY 16 maxit 500 calculateActMaps TRUE targets iris 5 par mfrow c 3 3 for i in 1 ncol inputs plotActMap model componentMaps i col rev topo colors 12 plotActMap model map col rev heat colors 12 splitForTrainingAndTest 65 plotActMap log model map 1 col rev heat colors 12 persp 1 model archParams mapX 1 model archParams mapY log model map 1 theta 30 phi 30 expand 0 5 col lightblue plotActMap model labeledMap model componentMaps model labeledUnits model map names model splitForTrainingAndTest Function to split data into training and test set Description Split the input and target values to a training and a test set Test set is taken from the end of the data If the data is to be shuffled this should be done before calling this function Usage splitForTrainingAndTest x y ratio 0 15 Arguments x inputs y targets ratio ratio of training and test sets default 15 of the data is used for testing Value a nam
5. learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled linOut sets the activation function of the output units to linear or logistic inputsTest a matrix with inputs to test the network targetsTest the corresponding targets for the test input jordan 27 Details Learning on Jordan networks Backpropagation algorithms for feed forward networks can be adapted for their use with this type of networks In SNNS there exist adapted versions of several backpropagation type algorithms for Jordan and Elman networks Network architecture A Jordan network can be seen as a feed forward network with additional context units in the input layer These context units take input from themselves direct feedback and from the output units The context units save the current state of the net In a Jordan net the number of context units and output units has to be the same Initialization of Jordan and Elman nets should be done with the default init function JE_Weights which has five parameters The first two parameters define an interval from which the forward connections are randomly chosen The third parameter gives the self excitation weights of the context units The fourth parameter gives the weights of context units between them and the fifth parameter gives the i
6. www ra cs uni tuebingen de SNNS See Also SnnsRObjectFactory Examples Not run demo encoderSnnsCLib Not run demo art1_lettersSnnsR Not run demo art2_tetraSnnsR Not run demo artmap_lettersSnnsR Not run demo eight_elmanSnnsR Not run demo rbf_irisSnnsR Not run demo rbf_sinSnnsR Not run demo rbfDDA_spiralsSnnsR Not run demo som_cubeSnnsR SnnsRObjectFactory 45 This is the demo eight_elmanSnnsR Here we train an Elman network and save a trained and an untrained version to disk as well as the used training data basePath lt data snnsData inputs lt snnsData eight_016 patL inputColumns snnsData eight_016 pat outputs lt snnsDatafeight_016 pat outputColums snnsDatafeight_016 pat snnsObject lt SnnsRObjectFactory snnsObject setLearnFunc JE_BP snnsObject setUpdateFunc JE_Order snnsObject setUnitDefaults 1 0 1 0 1 Act_Logistic Out_Identity snnsObject elman_createNet c 2 8 2 c 1 1 1 FALSE patset lt snnsObject createPatSet inputs outputs snnsObject setCurrPatSet patset set_no snnsObject initializeNet c 1 0 1 0 0 3 1 0 0 5 snnsObject shufflePatterns TRUE snnsObject DefTrainSubPat snnsObject saveNet paste basePath eight_elmanSnnsR_untrained net sep eight_elmanSnnsR_untrained parameters lt c 0 2 0 0 0 0 maxit lt 1000 error lt vector for i in 1 maxit res lt
7. rci tordid 444643 s 34 gy ra u k A ME a a 16 denormalizeData o eere sa s ee 17 DIVA 2 cad ban 8p ee Gk eee ba dy bee ee A Se A SO 18 CMAN se rk k ek OR o SEES ERS SERRE EEE S aka kiu 19 encodeClassLabels 1 3 cs s Sb we Oe Re A we a 21 exportToSnnsNetPile gt s pcoc c b a bak EE Ba bala Bes B k Sk 4 22 extractNotinlo 3 1 1 0 64 24 3 8 k SSR EEE Sr b 438 REE hv bls EGS 23 getNormParameters oo ces s l s s u s a s s 23 petSnnsRDemne qe sku s Var b s kadnkkleaask ad o V ka Eee au 24 getSnnsRFunctionTable 2 2 0 u u u kk k k k a k k k k k k k k R k eee 23 INPUICO LUMOS iw ed sori ea A a a A ee a 23 iO R A 26 matrixToActMapList iii sss u s s s k k a k k k k k k k k k k k a 28 DID AR rro e a O A e Bis eke 14 Pike 29 NormalizeData s ss 55 20 05 84 BER ads bba r r k a a ya l 31 normTrainingAndTestSet iis ii s s s k k k k k k k k k k k k k k a 32 OUtPUICOIUDINS gnu 2 B AAA AA saks h 24 U 33 plotActMap fc e 2 stk k k du fob rr Mae ge ee Be hole de Ga la 33 plotIterativeError 2 ee su 34 plotRegressionErtor s sene sne eee BAR Bee e BEES Se Bae a SS 34 PltROC 4 4 0 bee Ts bada Shea eee aes Cea ee dae bh bane eed 35 PLOdICLISONS is ek eS ee e Ew Be A AO ta ek aw 35 PEE ISODS a ot ee Pa Get e ea REDD doe SENS ERED CH OEE HOY 36 DE ar OR Roe AA ee eb be eA eee EG Ae kbbikbkkak 4 a 36 TOIDDA ia a e a lao ee PAE
8. snnsObject learnAllPatterns parameters if res 1 1 0 print paste Error at iteration i res sep error i lt res 2 error 1 500 plot error type 1 snnsObject saveNet paste basePath eight_elmanSnnsR net sep eight_elmanSnnsR snnsObject saveNewPatterns paste basePath eight_elmanSnnsR pat sep patset set_no SnnsRObjectFactory SnnsR object factory 46 SnnsRObjectMethodCaller Description Object factory to create a new object of type SnnsR class Usage SnnsRObjectFactory Details This function creates a new object of class SnnsR class initializes its only slot variables with a new environment generates a new C object of class SnnsCLib and an empty object serialization See Also SnnsR class Examples mySnnsObject lt SnnsRObjectFactory mySnnsObject setLearnFunc Quickprop mySnnsObject setUpdateFunc Topological_Order SnnsRObjectMethodCaller Method caller for SnnsR objects Description Enable calling of C functions as methods of SnnsR class objects Usage S4 method for signature SnnsR x name Arguments x object of class SnnsR class name function to call SnnsRObject createNet 47 Details This function makes methods of SnnsR__ and SnnsCLib__ accessible via If no SnnsR__ method is present then the according SnnsCLib__ method is called This enables a very flexible method handling To mask a method from Snn
9. 1 0 for both is usually fine The only learning function suitable for ARTI is ART1 Update functions are ART1_Stable and ART1_Synchronous The difference between the two is that the first one updates until the network is in a stable state and the latter one only performs one update step Both the learning function and the update functions have one parameter the vigilance parameter In its current implementation the network has two dimensional input The matrix x contains all one dimensional input patterns Internally every one of these patterns is converted to a two dimensional pattern using parameters dimX and dimY The parameter f2Units controls the number of units in the recognition layer and therewith the maximal amount of clusters that are assumed to be present in the input patterns A detailed description of the theory and the parameters is available from the SNNS documentation and the other referenced literature Value an rsnns object The fitted values member of the object contains a list of two dimensional activation patterns References Carpenter G A 8 Grossberg S 1987 A massively parallel architecture for a self organizing neural pattern recognition machine Comput Vision Graph Image Process 37 54 115 Grossberg S 1988 Adaptive pattern classification and universal recoding I parallel devel opment and coding of neural feature detectors MIT Press Cambridge MA USA chapter I pp 243 258 art2
10. 9 Herrmann K U 1992 ART Adaptive Resonance Theory Architekturen Implementierung und Anwendung Master s thesis IPVR University of Stuttgart in German Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German See Also art2 artmap Examples Not run demo art1_letters Not run demo art1_lettersSnnsR data snnsData patterns lt snnsData art1_letters pat inputMaps lt matrixToActMapList patterns nrow 7 par mfrow c 3 3 for i in 1 9 plotActMap inputMaps i model lt art1 patterns dimX 7 dimY 5 encodeClassLabels model fitted values art2 Create and train an art2 network Description ART is very similar to ARTI but for real valued input See art1 for more information Opposed to the ART1 implementation the ART2 implementation does not assume two dimensional input Usage art2 x Default S3 method art2 x f2Units 5 maxit 100 initFunc ART2_Weights initFuncParams c 0 9 2 learnFunc ART2 learnFuncParams c 0 98 10 10 0 1 0 updateFunc ART2_Stable updateFuncParams c 0 98 10 10 0 1 0 shufflePatterns TRUE 10 art2 Arguments x a matrix with training inputs for the network a additional fun
11. Appl Opt 26 23 4919 4930 Grossberg S 1988 Adaptive pattern classification and universal recoding I parallel devel opment and coding of neural feature detectors MIT Press Cambridge MA USA chapter I pp 243 258 Herrmann K U 1992 ART Adaptive Resonance Theory Architekturen Implementierung und Anwendung Master s thesis IPVR University of Stuttgart in German Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German artmap 11 See Also art1 artmap Examples Not run demo art2_tetra Not run demo art2_tetraSnnsR data snnsData patterns lt snnsData art2_tetra_med pat model lt art2 patterns f2Units 5 learnFuncParams c 0 99 20 20 0 1 0 updateFuncParams c 0 99 20 20 0 1 0 model testPatterns lt snnsData art2_tetra_high pat predictions lt predict model testPatterns Not run library scatterplot3d Not run par mfrow c 2 2 Not run scatterplot3d patterns pch encodeClassLabels model fitted values Not run scatterplot3d testPatterns pch encodeClassLabels predictions artmap Create and train an artmap network Description An ARTMAP performs supervised learning It consists of two coupled ART networks In theory
12. Eee BS A we eh 38 readPatBlle zd e g dite Ege NOG Bits E Hate AS See is Bike Be rs 40 Te dResFile o scene eA u 4 A eae ba ee ee 40 resolveSnnsRDemne y 0005 ee EE SUS E e Re ee 41 rsansObjectEactory x vx s ers ob ote er b SR hs sada a 41 savePatFllS oxicorte A a ae uu 43 setSmisRSecd Values 6 4 Soe si sv r k OE ERS See ee RG Sok oo 43 Sans Datas ede e g Ag u Be Beedle SG Gwe ORES BE Ae HSS 43 SONSR Cla8S 4 14 4 cea le e wae eae Shee dee dae eae ew es 44 sonsRObjeciFactory presos E Ee ER ESSE RES ROR ERASER ERE 45 SnnsRObjectMethodCaller 2 2 ee 46 SnnsRObject createNet 2 ee 47 SnnsRObject createPatSet 2 ee 48 SnnsRObject extractNetInfo 2 ee 48 SnnsRObject extractPatterns 222 ee 49 SnnsRObject genericPredictCurrPatSet 2 oo o 49 SnnsRObject getAllIHiddenUnits 2 ee 50 SnnsRObject getAllInputUnits 2 ee 50 SnnsRObject getAllOutputUnits 2 ee 51 RSNNS package 3 SnnsRObject getAllUnits 1 2 2 2212 22222 2 k 2 k k k k k k k k k k k k k k a al SnnsRObject getAMUnitsTType o o 32 SnnsRObject getCompleteWeightMatrix 22122222222 a 52 SnnsRObject getInfoHeader 2 iii u u k u k k k k k k k k k k k 53 SnnsRObject getSiteDefinitions iii i u k kk k k k k k k k k 53 SnnsRObject getTypeDefinitions 2 2 22 u u 2 u k k k k k k k k 2 k k Q 54 SnnsRObject getUnitDefinitions ssp s 2 4 k o 54
13. JE_BP learnFuncParams c 0 2 updateFunc JE_Order updateFuncParams c 0 shufflePatterns FALSE linOut TRUE outContext FALSE inputsTest NULL targetsTest NULL Arguments x a matrix with training inputs for the network additional function parameters currently not used y the corresponding targets values size number of units in the hidden layer s maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled linOut sets the activation function of the output units to linear or logistic outContext if TRUE the context units are also output units untested inputsTest a matrix with inputs to test the network targetsTest the corresponding targets for the test input Details Learning in Elman networks Same as in Jordan networks see jordan Network architecture The difference between Elman and Jordan networks is that in an Elman net work the context units get input not from the output units but from the hidden units Furthermore there is no direct feedback in the context units In an Elman net the number of context units and hidden units has to be the same The main advantage of Elman ne
14. SnnsR extractNetInfo Value a list of data frames containing information extracted from the network SnnsRObject extractPatterns Extract the current pattern set to a matrix Description SnnsR low level function that extracts all patterns of the current pattern set and returns them as a matrix Columns are named with the prefix in or out respectively Usage S4 method for signature SnnsR extractPatterns Value a matrix containing the patterns of the currently loaded patern set SnnsRObject genericPredictCurrPatSet Predict values with a trained net Description SnnsR low level function for generic prediction with a trained net Usage S4 method for signature SnnsR genericPredictCurrPatSet units updateFuncParams c 0 0 Arguments units the units that define the output updateFuncParams the parameters for the update function the function has to be already set Value the predicted values 50 SmnsRObject getAllInputUnits SnnsRObject getAllHiddenUnits Get all hidden units of the net Description SnnsR low level function to get all units from the net with the ttype UNIT_HIDDEN This func tion calls SnnsRObject getAllUnitsTType with the parameter UNIT_HIDDEN Usage S4 method for signature SnnsR getAllHiddenUnits Value a vector with integer numbers identifying the units See Also SnnsRObject getAllUnitsTType SnnsRObject getAllInputUnits Get all input units of the n
15. nRowInputsTargets same but for the target value input units nRowUnitsRecLayerTrain same but for the recognition layer of the training data ART network nRowUnitsRecLayerTargets same but for the recognition layer of the target data ART network initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled Details See also the details section of art1 The two ARTI networks are connected by a map field The input of the first ARTI network is the training input the input of the second network are the target values the teacher signals The two networks are often called ARTa and ARTD we call them here training data network and target data network In analogy to the ARTI and ART2 implementations there are one initialization function one learn ing function and two update functions present that are suitable for ARTMAP The parameters are basically as in ARTI but for two networks The learning function and the update functions have 3 parameters the vigilance parameters of the two ARTI networks and an additional vigilance pa rameter for inter ART reset control The initialization function has four parameters two for every ARTI network A detailed descrip
16. values predict model testData assoz Create and train an auto associative memory Description The autoassociative memory performs clustering by finding a prototype to the given input The implementation assumes two dimensional input and output cf art1 14 assoz Usage assoz x Default S3 method assoz x dimX dimY maxit 100 initFunc RM_Random_Weights initFuncParams c 1 1 learnFunc RM_delta learnFuncParams c 0 01 100 0 0 0 updateFunc Auto_Synchronous updateFuncParams c 5Q shufflePatterns TRUE Arguments x a matrix with training inputs for the network additional function parameters currently not used dimX x dimension of inputs and outputs dimY y dimension of inputs and outputs maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled Details The default initialization and update functions are the only ones suitable for this kind of network The update function takes one parameter which is the number of iterations that will be performed The default of 50 usually does not have to be modified For learning RM_delta and
17. 0ut FALSE names model Jordan par mfrow c 3 3 plotIterativeError modelJordan plotRegressionError patterns targetsTrain modelJordan fitted values plotRegressionError patterns targetsTest modelJordan fittedTestValues hist modelJordan fitted values patterns targetsTrain col lightblue plot inputs type 1 plot inputs 1 100 type 1 lines outputs 1 100 col red lines modelJordan fitted values 1 100 col green matrixToActMapList Convert matrix of activations to activation map list Description Organize a matrix containing 1d vectors of network activations as 2d maps Usage matrixToActMapList m nrow 0 ncol 0 Arguments m the matrix containing one activation pattern in every row nrow number of rows the resulting matrices will have ncol number of columns the resulting matrices will have Details The input to this function is a matrix containing in each row an activation pattern output of a neural network This function uses vectorToActMap to reorganize the matrix to a list of matrices whereby each row of the input matrix is converted to a matrix in the output list Value a list containing the activation map matrices mlp 29 See Also vectorToActMap plotActMap mlp Create and train a multi layer perceptron MLP Description This function creates a multilayer perceptron MLP and trains it MLPs are fully connected feed forward networks and probably the most co
18. 5 19 26 27 42 encodeClassLabels 7 16 21 exportToSnnsNetFile 22 23 extractNetInfo 23 66 extractNetInfo SnnsR method SnnsRObject extractNetInfo 48 extractPatterns SnnsR method SnnsRObject extractPatterns 49 70 genericPredictCurrPatSet SnnsR method SnnsRObject genericPredictCurrPatSet 49 getAllHiddenUnits SnnsR method SnnsRObject getAllHiddenUnits 50 getAllInputUnits SnnsR method SnnsRObject getAllInputUnits 50 getAllOutputUnits SnnsR method SnnsRObject getAllOutputUnits 31 getAllUnits SnnsR method SnnsRObject getAllUnits 51 getAllUnitsTType SnnsR method SnnsRObject getAl1UnitsTType 52 getCompleteWeightMatrix SnnsR method SnnsRObject getCompleteWeightMatrix IZ getInfoHeader SnnsR method SnnsRObject getInfoHeader 53 getNormParameters 17 23 32 33 getSiteDefinitions SnnsR method SnnsRObject getSiteDefinitions 53 getSnnsRDefine 24 41 getSnnsRFunctionTable 25 getTypeDefinitions SnnsR method SnnsRObject getTypeDefinitions 54 getUnitDefinitions SnnsR method SnnsRObject getUnitDefinitions 54 getUnitsByName SnnsR method SnnsRObject getUnitsByName 55 getWeightMatrix SnnsR method SnnsRObject getWeightMatrix INDEX 39 initializeNet SnnsR method SnnsRObject initializeNet 56 inputColumns 25 jordan 4 5 19 21 26 42 matrixToActMapList 28 34 68 mlp 4 5 29 36 42 67 normalizeData 17 23 24 31 32 33 normTrain
19. Adaptive resonance theory ART networks perform clustering by finding prototypes They are mainly designed to solve the stability plasticity dilemma which is one of the central problems in neural networks in the following way new input patterns may generate new prototypes plasticity but patterns already present in the net represented by their prototypes are only altered by similar new patterns not by others stability ARTI is for binary inputs only if you have real valued input use art2 instead Usage artl x Default S3 method art1 x dimX dimY f2Units nrow x maxit 100 initFunc ART1_Weights initFuncParams c 1 1 learnFunc ART1 learnFuncParams c 0 9 0 0 updateFunc ART1_Stable updateFuncParams c 0 shufflePatterns TRUE Arguments x a matrix with training inputs for the network additional function parameters currently not used dimX x dimension of inputs and outputs dimY y dimension of inputs and outputs f2Units controls the number of clusters assumed to be present maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function 8 artl updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled
20. CurrPatSetWinn amp p8Spsntr burrPatSetWinnersSpanTree SnnsR method 60 SnnsR__train SnnsRObject train 60 SnnsR__whereAreResults SnnsRObject whereAreResults 62 SnnsRObject createNet 47 SnnsRObject createPatSet 48 SnnsRObject extractNetInfo 23 48 SnnsRObject extractPatterns 40 49 SnnsRObject genericPredictCurrPatSet 49 SnnsRObject getAllHiddenUnits 50 52 SnnsRObject getAllInputUnits 50 52 SnnsRObject getAllOutputUnits 51 52 SnnsRObject getAllUnits 51 SnnsRObject getAllUnitsTType 50 51 52 36 57 SnnsRObject getCompleteWeightMatrix 52 68 SnnsRObject getInfoHeader 53 SnnsRObject getSiteDefinitions 53 SnnsRObject getTypeDefinitions 54 SnnsRObject getUnitDefinitions 54 SnnsRObject getUnitsByName 55 SnnsRObject getWeightMatrix 55 SnnsRObject initializeNet 47 56 SnnsRObject predictCurrPatSet 56 SnnsRObject resetRSNNS 57 SnnsRObject somPredictCurrPatSetWinnersSpanTree 60 splitForTrainingAndTest 32 33 65 summary rsnns 23 66 toNumericClassLabels 66 train 42 67 train SnnsR method SnnsRObject train 60 vectorToActMap 28 29 34 68 weightMatrix 68 whereAreResults SnnsR method SnnsRObject whereAreResults 62
21. Details Learning in an ART network works as follows A new input is intended to be classified according to the prototypes already present in the net The similarity between the input and all prototypes is calculated The most similar prototype is the winner If the similarity between the input and the winner is high enough defined by a vigilance parameter the winner is adapted to make it more similar to the input If similarity is not high enough a new prototype is created So at most the winner is adapted all other prototypes remain unchanged The architecture of an ART network is the following ART is based on the more general concept of competitive learning The networks have two fully connected layers in both directions the input comparison layer and the recognition layer They propagate activation back and forth reso nance The units in the recognition layer have lateral inhibition so that they show a winner takes all behaviour i e the unit that has the highest activation inhibits activation of other units so that after a few cycles its activation will converge to one whereas the other units activations converge to zero ART stabilizes this general learning mechanism by the presence of some special units For details refer to the referenced literature The default initialization function ART1_Weights is the only one suitable for ART1 networks It has two parameters which are explained in the SNNS User Manual pp 189 A default of
22. Hebbian functions can be used though the first one usually performs better A more detailed description of the theory and the parameters is available from the SNNS documen tation and the other referenced literature Value an rsnns object The fitted values member contains the activation patterns for all inputs confusionMatrix 15 References Palm G 1980 On associative memory Biological Cybernetics 36 19 31 Rojas R 1996 Neural networks a systematic introduction Springer Verlag Berlin Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS See Also artl art2 Examples Not run demo assoz_letters Not run demo assoz_lettersSnnsR data snnsData patterns lt snnsData art1_letters pat model lt assoz patterns dimX 7 dimY 5 actMaps lt matrixToActMapList model fitted values nrow 7 par mfrow c 3 3 for i in 1 9 plotActMap actMaps i confusionMatrix Computes a confusion matrix Description The confusion matrix shows how many times a pattern with the real class x was classified as class y A perfect method should result in a diagonal matrix All values not on the diagonal are errors of the method Usage confusionMatrix targets predictions Arguments targets the known correct target values predictions the corresp
23. Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS javaNNS the sucessor of the original SNNS with a Java GUI http www ra cs uni tuebingen de software JavaNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley Other resources A function to plot networks from the mlp function https beckmw wordpress com 2013 11 14 visualizing neural networks in r update See Also mlp dlvq rbf rbfDDA elman jordan som art1 art2 artmap assoz 6 analyzeClassification analyzeClassification Converts continuous outputs to class labels Description This function converts the continuous outputs to binary outputs that can be used for classification The two methods 402040 and winner takes all WTA are implemented as described in the SNNS User Manual 4 2 Usage analyzeClassification y method WTA 1 h 0 Arguments y inputs method WTA or 402040 1 lower bound e g in 402040 1 0 4 h upper bound e g in 402040 h 0 6 Details The following text is an edited citation from the SNNS User Manual 4 2 pp 269 402040 A pattern is recognized as classified correctly if 1 the output of exactly one output unit is gt h ii the teaching output of this unit is the maximum teaching output gt 0 of the pattern 111 the output of all other output units is lt 1 A pattern is recognized as classified
24. Package RSNNS June 12 2015 Maintainer Christoph Bergmeir lt c bergmeir decsai ugr es gt License LGPL gt 2 file LICENSE Title Neural Networks in R using the Stuttgart Neural Network Simulator SNNS LinkingTo Rcpp Type Package LazyLoad yes Author Christoph Bergmeir and Jos M Benitez Description The Stuttgart Neural Network Simulator SNNS is a library containing many standard implementations of neural networks This package wraps the SNNS functionality to make it available from within R Using the RSNNS low level interface all of the algorithmic functionality and flexibility of SNNS can be accessed Furthermore the package contains a convenient high level interface so that the most common neural network topologies and learning algorithms integrate seamlessly into R Version 0 4 7 URL http sci2s ugr es dicits software RSNNS Date 2015 06 12 Depends R gt 2 10 0 methods Rcpp gt 0 8 5 Suggests scatterplot3d NeuralNetTools Encoding UTF 8 NeedsCompilation yes Repository CRAN Date Publication 2015 06 12 10 49 38 R topics documented RSNNS package 3 eno SARE ENS ee bee SPE AA analyzeClassification 13134 buss skak eee GARR E ERR ee V R topics documented Ml sss ew ale ES eae aE Leal Pa a RA ee oe 7 aii asa ia a r bate Pe ee ie 9 AT MAD pad e e Seta Ob See ee bet o ete Ee bee a to do 11 AO A ra A dal A ee at 13 CONTUSION MAATTI 2 esbirros o hd 35 ku 15 decodeClassLabels
25. SnnsRObject getUnitsByName i ii u k 2 k k k k k k k k k k k 2 55 SnnsRObject getWeightMatrix 2 ee 55 SnnsRObject initializeNet 2 ee 56 SnnsRObject predictCurrPatSet oaoa ee 56 SnnsRObject resetRSNNS 0 ee 57 SnnsRObject setTTypeUnitsActFunc o o 57 SnnsRObject setUnitDefaults o oaoa a 58 SnnsRObject somPredictComponentMaps o e e a 58 SnnsRObject somPredictCurrPatSetWinners ooo a 59 SnnsRObject somPredictCurrPatSetWinnersSpanTree o oo a 60 SnnsRObject train s se rrer ee 60 SnnsRObject whereAreResults o ee 62 SODE 2er ia aKa iaa o E aaa The a d so BY R RA Theda ap 62 splitForTrainingAndTest aoaaa ee 65 summary rsmnS 2 pehta e a ras i ak os a Aa ah a E iip l r sko l ai 66 toNumericClassLabels e 66 Val 2 u s stk b E Blk BOR vK KUR a SER Ee b R PR aes 67 vectorPoActMap 213 spk Ga bk a ark bd 44 a phat blaa pk h 4 68 Wei DIMat lk 3 44534 u s s Gd k w eee bid Ad BESS 68 Index 70 RSNNS package Getting started with the RSNNS package Description The Stuttgart Neural Network Simulator SNNS is a library containing many standard implemen tations of neural networks This package wraps the SNNS functionality to make it available from within R Details If you have problems using RSNNS find a bug or have suggestions please contact the package maintainer by email instead of writing to the gen
26. ain iris targetsTrain summary model plotIterativeError model 40 readResFile readPatFile Load data from a pat file Description This function generates an SnnsR class object loads the given pat file there as a pattern set and then extracts the patterns to a matrix using SnnsRObject extractPatterns Usage readPatFile filename Arguments filename the name of the pat file Value a matrix containing the data loaded from the pat file readResFile Rudimentary parser for res files Description This function contains a rudimentary parser for SNNS res files It is completely implemented in R and doesn t make use of SNNS functionality Usage readResFile filename Arguments filename the name of the res file Value a matrix containing the predicted values that were found in the res file resolveSnnsRDefine 41 resolveSnnsRDefine Resolve a define of the SNNS kernel Description Resolve a define of the SNNS kernel using a defines list All defines lists present can be shown with RSNNS SnnsDefines Usage resolveSnnsRDefine defList def Arguments defList the defines list from which to resolve the define from def the name of the define Value the value of the define See Also getSnnsRDefine Examples resolveSmnsRDefine topologicalUnitTypes UNIT_HIDDEN rsnnsObjectFactory Object factory for generating rsnns objects Description The object fact
27. ction parameters currently not used f2Units controls the number of clusters assumed to be present maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled Details As comparison of real valued vectors is more difficult than comparison of binary vectors the com parison layer is more complex in ART2 and actually consists of three layers With a more complex comparison layer also other parts of the network enhance their complexity In SNNS this enhanced complexity is reflected by the presence of more parameters in initialization learning and update function In analogy to the implementation of ARTI there are one initialization function one learning func tion and two update functions suitable for ART2 The learning and update functions have five parameters the initialization function has two parameters For details see the SNNS User Manual p 67 and pp 192 Value an rsnns object The fitted values member contains the activation patterns for all inputs References Carpenter G A amp Grossberg S 1987 ART 2 self organization of stable category recognition codes for analog input patterns
28. cture needed train the network with train In every rsnns object the iterative error is the summed squared error SSE of all patterns If the SSE is computed on the test set then it is weighted to take care of the different amount of patterns in the sets Value a partly initialized rsnns object See Also mlp dlvq rbf rbfDDA elman jordan som art1 art2 artmap assoz savePatFile 43 savePatFile Save data to a pat file Description This function generates an SnnsR class object loads the given data there as a pattern set and then uses the functionality of SNNS to save the data as a pat file Usage savePatFile inputs targets filename Arguments inputs a matrix with input values targets a matrix with target values filename the name of the pat file setSnnsRSeedValue DEPRECATED Set the SnnsR seed value Description DEPRECATED now just calls R s set seed that should be used instead Usage setSnnsRSeedValue seed Arguments seed the seed to use If 0 a seed based on the system time is generated snnsData Example data of the package Description This is data from the original SNNS examples directory ported to R and stored as one list The function readPatFile was used to parse all pattern files pat from the original SNNS examples directory Due to limitations of that function pattern files containing patterns with variable size were omitted Examples data snnsData names
29. dateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled lin0ut sets the activation function of the output units to linear or logistic Details The default functions do not have to be altered The learning function RBF DDA has three parameters a positive threshold and a negative threshold that controls adding units to the network and a parameter for display purposes in the original SNNS This parameter has no effect in RSNNS See p 74 of the original SNNS User Manual for details Value an rsnns object References Berthold M R amp Diamond J 1995 Boosting the Performance of RBF Networks with Dynamic Decay Adjustment in Advances in Neural Information Processing Systems MIT Press pp 521 528 Hudak M 1993 RCE classifiers theory and practice Cybernetics and Systems 23 5 483 515 Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Examples Not run demo iris Not run demo rbfDDA_spiralsSnnsR data iris iris lt iris sample 1 nrow iris length 1 nrow iris 1 ncol iris irisValues lt iris 1 4 irisTargets lt decodeClassLabels iris 5 iris lt splitForTrainingAndTest irisValues irisTargets ratio 0 15 iris lt normTrainingAndTestSet iris model lt rbfDDACiris inputsTr
30. e S4 method for signature SnnsR somPredictComponentMaps updateFuncParams c 0 0 0 0 1 0 SnnsRObject somPredictCurrPatSetWinners 59 Arguments updateFuncParams parameters passed to the networks update function Value a matrix containing all componant maps as Id vectors See Also som SnnsRObject somPredictCurrPatSetWinners Get most of the relevant results from a som Description SnnsR low level function to get most of the relevant results from a SOM Usage S4 method for signature SnnsR somPredictCurrPatSetWinners updateFuncParams c 0 0 0 0 1 0 saveWinnersPerPattern TRUE targets NULL Arguments updateFuncParams parameters passed to the networks update function saveWinnersPerPattern should a list with the winners for every pattern be saved targets optional target classes of the patterns Value a list with three elements nWinnersPerUnit For each unit the amount of patterns where this unit won is given So this is a 1d vector representing the normal version of the som winnersPerPattern a vector where for each pattern the number of the winning unit is given This is an intermediary result that normally won t be saved labeledUnits a matrix which if the targets parameter is given contains for each unit rows and each class present in the targets columns the amount of patterns of the class where the unit has won From the labeledUnits the labeledMap can be computed e g by
31. e Details The input to this function is a vector containing in each row an activation pattern output of a neural network This function reorganizes the vector to a matrix Normally only the number of rows nrow will be used Value a matrix containing the 2d reorganized input See Also matrixToActMapList plotActMap weightMatrix Function to extract the weight matrix of an rsnns object Description The function calls SnnsRObject getCompleteWeightMatrix and returns its result Function to extract the weight matrix of an rsnns object Usage weightMatrix object S3 method for class rsnns weightMatrix object weightMatrix Arguments object the rsnns object additional function parameters currently not used Value a matrix with all weights from all neurons present in the net 69 Index Topic SNNS RSNNS package 3 Topic data snnsData 43 Topic networks RSNNS package 3 Topic neural RSNNS package 3 Topic package RSNNS package 3 44 46 SnnsRObjectMethodCaller 46 SnnsR method SnnsRObjectMethodCal ler 46 analyzeClassification 6 22 art1 4 5 7 9 11 13 15 42 art2 4 5 7 9 9 13 15 42 artmap 4 5 9 11 11 42 assoz 4 5 13 42 confusionMatrix 15 createNet SnnsR method SnnsRObject createNet 47 createPatSet SnnsR method SnnsRObject createPatSet 48 decodeClassLabels 16 64 denormalizeData 17 24 32 33 dlvq 4 5 18 42 elman 4
32. ed list with the following elements inputsTrain a matrix containing the training inputs targetsTrain a matrix containing the training targets inputsTest a matrix containing the test inputs targetsTest a matrix containing the test targets Examples data iris shuffle the vector iris lt iris sample 1 nrow iris length 1 nrow iris 1 ncol iris irisValues lt iris 1 4 irisTargets lt decodeClassLabels iris 5 splitForTrainingAndTest irisValues irisTargets ratio 0 15 66 toNumericClassLabels summary rsnns Generic summary function for rsnns objects Description Prints out a summary of the network The printed information can be either all information of the network in the original SNNS file format or the information given by extractNetInfo This behaviour is controlled with the parameter origSnnsFormat Usage S3 method for class rsnns summary object origSnnsFormat TRUE Arguments object the rsnns object origSnnsFormat show data in SNNS s original format in which networks are saved or show output of extractNetInfo additional function parameters currently not used Value Either the contents of the net file that SNNS would generate from the object as a string Or the output of extractNetInfo See Also extractNetInfo toNumericClassLabels Convert a vector of class labels to a numeric vector Description This function converts a vector of class labels to a numeric
33. ense For regression normalizing also the targets is usually a good idea Usage normTrainingAndTestSet x dontNormTargets TRUE type norm Arguments x a list containing training and test data Usually the output of splitForTrainingAndTest dontNormTargets should the target values also be normalized type type of the normalization This parameter is passed to normalizeData Value a named list with the same elements as splitForTrainingAndTest but with normalized val ues The normalization parameters are appended to each member of the list as attributes as in normalizeData outputColumns 33 See Also splitForTrainingAndTest normalizeData denormalizeData getNormParameters Examples data iris shuffle the vector iris lt iris sample 1 nrow iris length 1 nrow iris 1 ncol iris irisValues lt iris 1 4 irisTargets lt decodeClassLabels iris 5 iris lt splitForTrainingAndTest irisValues irisTargets ratio 0 15 normTrainingAndTestSet iris outputColumns Get the columns that are targets Description This function extracts all columns from a matrix whose column names begin with out The example data of this package follows this naming convention Usage outputColumns patterns Arguments patterns matrix or data frame containing the patterns plotActMap Plot activation map Description Plot an activation map as a heatmap Usage plotActMap x Arguments xX the input da
34. epending on which calculation flags are switched on the som generates some the som For each unit the amount of patterns where this unit won is given a map for every input component showing where in the map this component leads to high activation a list containing for each pattern its activation map 1 e all unit activations The actMaps are an intermediary result from which all other results can be computed This list can be very long so normally it won t be saved winnersPerPattern labeledUnits labeledMap spanningTree References a vector where for each pattern the number of the winning unit is given Also an intermediary result that normally won t be saved a matrix which if the targets parameter is given contains for each unit rows and each class present in the targets columns the amount of patterns of the class where the unit has won From the labeledUnits the labeledMap can be computed e g by voting of the class labels for the final label of the unit a labeled som that is computed from labeledUnits using decodeClassLabels the result of the original SNNS function to calculate the map For each unit the last pattern where this unit won is present As the other results are more informative the spanning tree is only interesting if the other functions are too slow or if the original SNNS implementation is needed Kohonen T 1988 Self organization and associative memory Vol 8 Springer Verlag
35. er Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German Examples Not run demo iris Not run demo laser Not run demo encoderSnnsCLib data iris shuffle the vector iris lt iris sample 1 nrow iris length 1 nrow iris 1 ncol iris normalizeData 31 irisValues lt iris 1 4 irisTargets lt decodeClassLabels iris 5 irisTargets lt decodeClassLabels iris 5 valTrue 0 9 valFalse 0 1 iris lt splitForTrainingAndTest irisValues irisTargets ratio 0 15 iris lt normTrainingAndTestSet iris model lt mlp iris inputsTrain iris targetsTrain size 5 learnFuncParams c 0 1 maxit 50 inputsTest iris inputsTest targetsTest iris targetsTest summary model model weightMatrix model extractNetInfo model par mfrow c 2 2 plotIterativeError model predictions lt predict model iris inputsTest plotRegressionError predictions 2 iris targetsTestL 2 confusionMatrix iris targetsTrain fitted values model confusionMatrix iris targetsTest predictions plotROC fitted values model 2 iris targetsTrain 2 plotROC predictions 2 iris targetsTestL 2 confusion matrix with 402040 method confusionMatrix iris targetsTrain encodeClassLabels fitted values model method 402040 1 0 4 h 0 6 normalizeData Data normali
36. eral R lists or contacting the authors of the original SNNS software If you use the package please cite the following work in your publications Bergmeir C and Benitez J M 2012 Neural Networks in R Using the Stuttgart Neural Network Simulator RSNNS Journal of Statistical Software 46 7 1 26 http www jstatsoft org v46 107 The package has a hierarchical architecture with three levels RSNNS package e RSNNS high level api rsnns e RSNNS low level api SnnsR The api of our C port of SNNS SnnsCLib Many demos for using both low level and high level api of the package are available To get a list of them type library RSNNS demo It is a good idea to start with the demos of the high level api which is much more convenient to use E g to access the iris classification demo type demo iris or for the laser regression demo type demo laser As the high level api is already quite powerful and flexible you ll most probably normally end up using one of the functions mlp dlvq rbf rbfDDA elman jordan som art1 art2 artmap or assoz with some pre and postprocessing These S3 classes are all subclasses of rsnns You might also want to have a look at the original SNNS program and the SNNS User Manual 4 2 especially pp 67 87 for explications on all the parameters of the learning functions and pp 145 215 for detailed theoretical explications of the methods and advice on their use And there is als
37. et Description SnnsR low level function to get all units from the net with the ttype UNIT_INPUT This function calls SnnsRObject getAllUnitsTType with the parameter UNIT_INPUT Usage S4 method for signature SnnsR getAllInputUnits Value a vector with integer numbers identifying the units See Also SnnsRObject getAllUnitsTType SnnsRObject getAllOutputUnits 51 SnnsRObject getAllOutputUnits Get all output units of the net Description SnnsR low level function to get all units from the net with the ttype UNIT_OUTPUT This function calls SnnsRObject getAl1UnitsTType with the parameter UNIT_OUTPUT Usage S4 method for signature SnnsR getAll0utputUnits Value a vector with integer numbers identifying the units See Also SnnsRObject getAllUnitsTType SnnsRObject getAllUnits Get all units present in the net Description Get all units present in the net Usage S4 method for signature SnnsR getAllUnits Value a vector with integer numbers identifying the units 52 SnnsRObject getComplete WeightMatrix SnnsRObject getAllUnitsTType Get all units in the net of a certain ttype Description SnnsR low level function to get all units in the net of a certain ttype Possible ttype defined by SNNS are among others UNIT_OUTPUT UNIT_INPUT and UNIT_HIDDEN For a full list call RSNNS SnnsDefines topologicalUnitTypes As this is an SnnsR low level function you may
38. ghtMatrix 52 SnnsR__getInfoHeader SnnsRObject getInfoHeader 53 SnnsR__getSiteDefinitions SnnsRObject getSiteDefinitions 53 SnnsR__getTypeDefinitions SnnsRObject getTypeDefinitions 54 SnnsR__getUnitDefinitions SnnsRObject getUnitDefinitions 54 SnnsR__getUnitsByName SnnsRObject getUnitsByName 595 SnnsR__getWeightMatrix SnnsRObject getWeightMatrix 59 SnnsR__initializeNet 72 SnnsRObject initializeNet 56 SnnsR__predictCurrPatSet SnnsRObject predictCurrPatSet 56 SnnsR__resetRSNNS SnnsRObject resetRSNNS 57 SnnsR__setTTypeUnitsActFunc SnnsRObject setTTypeUnitsActFunc 57 SnnsR__setUnitDefaults SnnsRObject setUnitDefaults 58 SnnsR__somPredictComponentMaps INDEX SnnsRObject setTTypeUnitsActFunc 57 SnnsRObject setUnitDefaults 58 SnnsRObject somPredictComponentMaps 58 SnnsRObject somPredictCurrPatSetWinners 59 SnnsRObject somPredictCurrPatSetWinnersSpanTree 60 SnnsRObject train 47 60 67 SnnsRObject whereAreResults 56 62 SnnsRObjectFactory 44 45 SnnsRObjectMethodCaller 46 som 4 5 18 42 59 60 62 SnnsRObject somPredictComponentMaps SomPredictComponentMaps SnnsR method 58 SnnsR__somPredictCurrPatSetWinners SnnsRObject somPredictComponentMaps 58 SnnsRObject somPredictCurrPatSetWinnepapredictCurrPatSetWinners SnnsR method 59 SnnsR__somPredictCurrPatSetWinnersSpanTree SnnsRObject somPredictCurrPatSetWinners 59 SnnsRObject somPredict
39. he networks generated with RSNNS Most of the example data included in SNNS is also present in this package see snnsData Additional information is also available at the project website http sci2s ugr es dicits software RSNNS RSNNS package 5 Author s Christoph Bergmeir lt c bergmeir decsai ugr es gt and Jos M Benitez lt j m benitez decsai ugr es gt DiCITS Lab Sci2s group DECSAI University of Granada http dicits ugr es http sci2s ugr es References Bergmeir C and Ben tez J M 2012 Neural Networks in R Using the Stuttgart Neural Network Simulator RSNNS Journal of Statistical Software 46 7 1 26 http www jstatsoft org v46 107 General neural network literature Bishop C M 2003 Neural networks for pattern recognition University Press Oxford Haykin S S 1999 Neural networks a comprehensive foundation Prentice Hall Upper Saddle River NJ Kriesel D 2007 A Brief Introduction to Neural Networks http www dkriesel com Ripley B D 2007 Pattern recognition and neural networks Cambridge University Press Cam bridge Rojas R 1996 Neural networks a systematic introduction Springer Verlag Berlin Rumelhart D E Clelland J L M amp Group P R 1986 Parallel distributed processing explo rations in the microstructure of cognition Mit Cambridge MA etc Literature on the original SNNS software Zell A et al 1998 SNNS Stuttgart Neural
40. ict rsnns Generic predict function for rsnns object Description Predict values using the given network Usage S3 method for class rsmns predict object newdata Arguments object the rsnns object newdata the new input data which is used for prediction additional function parameters currently not used Value the predicted values 36 rbf print rsnns Generic print function for rsnns objects Description Print out some characteristics of an rsnns object Usage S3 method for class rsnns print x Arguments x the rsnns object additional function parameters currently not used rbf Create and train a radial basis function RBF network Description The use of an RBF network is similar to that of an mlp The idea of radial basis function net works comes from function interpolation theory The RBF performs a linear combination of n basis functions that are radially symmetric around a center prototype Usage rbf x Default S3 method rbf x y size c 5 maxit 100 initFunc RBF_Weights initFuncParams c 1 0 0 02 0 04 learnFunc RadialBasisLearning learnFuncParams c le 05 0 le 05 0 1 0 8 updateFunc Topological_Order updateFuncParams c 0 shufflePatterns TRUE linOut TRUE inputsTest NULL targetsTest NULL Arguments xX a matrix with training inputs for the network additional function parameters currently not used
41. incorrectly if 1 and 111 hold as above but for 11 holds that the teaching output is not the maximum teaching output of the pattern or there is no teaching output gt 0 A pattern is recognized as unclassified in all other cases The method derives its name from the commonly used default values 1 0 4 h 0 6 WTA A pattern is recognized as classified correctly if i there is an output unit with the value greater than the output value of all other output units this output value is supposed to be a ii a gt h iii the teaching output of this unit is the maximum teaching output of the pattern gt 0 iv the output of all other units is lt a 1 A pattern is recognized as classified incorrectly if 1 11 and iv hold as above but for 111 holds that the teaching output of this unit is not the maximum teaching output of the pattern or there is no teaching output gt 0 A pattern is recognized as unclassified in all other cases Commonly used default values for this method are 1 0 0 h 0 0 Value the position of the winning unit i e the winning class or zero if no classification was done art 7 References Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS See Also encodeClassLabels arti Create and train an artl network Description
42. ingAndTestSet 32 outputColumns 33 plotActMap 29 33 68 plotIterativeError 34 plotRegressionError 34 plotROC 35 predict rsnns 35 predictCurrPatSet SnnsR method SnnsRObject predictCurrPatSet 56 print rsnns 36 rbf 4 5 36 42 rbfDDA 4 5 38 42 readPatFile 40 43 readResFile 40 resetRSNNS SnnsR method SnnsRObject resetRSNNS 57 resolveSnnsRDefine 24 41 RSNNS RSNNS package 3 rsnns 4 8 10 13 14 19 21 23 27 30 34 37 39 64 66 67 69 rsnns rsnnsObjectFactory 41 RSNNS package 3 rsnnsObjectFactory 41 savePatFile 43 setSnnsRSeedValue 43 setTTypeUnitsActFunc SnnsR method SnnsRObject setTTypeUnitsActFunc aT setUnitDefaults SnnsR method SnnsRObject setUnitDefaults 58 snnsData 4 43 SnnsR class 40 43 44 46 71 SnnsR__createNet SnnsRObject createNet 47 SnnsR__createPatSet SnnsRObject createPatSet 48 SnnsR__extractNetInfo SnnsRObject extractNetInfo 48 SnnsR__extractPatterns SnnsRObject extractPatterns 49 SnnsR__genericPredictCurrPatSet SnnsRObject genericPredictCurrPatSet 49 SnnsR__getAllHiddenUnits SnnsRObject getAllHiddenUnits 50 SnnsR__getAllInputUnits SnnsRObject getAllInputUnits 50 SnnsR__getAllOutputUnits SnnsRObject getAllOutputUnits 51 SnnsR__getAllUnits SnnsRObject getAllUnits 51 SnnsR__getAllUnitsTType SnnsRObject getAl1UnitsTType 52 SnnsR__getCompleteWeightMatrix SnnsRObject getCompleteWei
43. ining the output method of the net Possible values are artl art2 n wow wow artmap assoz som output Details Depending on the network architecture output is present in hidden units in output units etc In some network types the output units have a certain name prefix in SNNS This function finds the output units according to certain network types The type is specified by outputMethod If the given outputMethod is unknown the function defaults to output Value a list of numbers identifying the units som Create and train a self organizing map SOM Description This function creates and trains a self organizing map SOM SOMs are neural networks with one hidden layer The network structure is similar to LVQ but the method is unsupervised and uses a notion of neighborhood between the units The general idea is that the map develops by itself a notion of similarity among the input and represents this as spatial nearness on the map Every hidden unit represents a prototype The goal of learning is to distribute the prototypes in the feature space such that the probability density of the input is represented well SOMs are usually built with 1d 2d quadratic 2d hexagonal or 3d neighborhood so that they can be visualized straightforwardly The SOM implemented in SNNS has a 2d quadratic neighborhood som 63 Usage som x Default S3 method som x mapX 16 mapY 16 maxit 100 initFu
44. initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled Details The input data has to be normalized in order to use DLVQ Learning in DLVQ For each class a mean vector prototype is calculated and stored in a newly generated hidden unit Then the net is used to classify every pattern by using the nearest proto type If a pattern gets misclassified as class y instead of class x the prototype of class y is moved away from the pattern and the prototype of class x is moved towards the pattern This procedure is repeated iteratively until no more changes in classification take place Then new prototypes are in troduced in the net per class as new hidden units and initialized by the mean vector of misclassified patterns in that class elman 19 Network architecture The network only has one hidden layer containing one unit for each proto type The prototypes hidden units are also called codebook vectors Because SNNS generates the units automatically and does not need their number to be specified in advance the procedure is called dynamic LVQ in SNNS The default initialization learning and update functions are the only ones suitable for this kind of network The three parameters of the learning function specify two learni
45. l are returned Value a list containing information extracted from the network see SnnsRObject extractNetInfo See Also SnnsRObject extractNetInfo getNormParameters Get normalization parameters of the input data Description Get the normalization parameters that are appended by normalizeData as attributes to the input data Usage getNormParameters x Arguments x input data 24 getSnnsRDefine Details This function is equivalent to calling attr x normParams Value the parameters generated by an earlier call to normalizeData See Also normalizeData denormalizeData getSnnsRDefine Get a define of the SNNS kernel Description Get a define of the SNNS kernel from a defines list All defines lists present can be shown with RSNNS SnnsDefines Usage getSnnsRDefine defList defValue Arguments defList the defines list from which to get the define from defValue the value in the list Value a string with the name of the define See Also resolveSnnsRDefine Examples getSnnsRDefine topologicalUnitTypes 3 getSnnsRDefine errorCodes 50 getSnnsRFunctionTable 25 getSnnsRFunctionTable Get SnnsR function table Description Get the function table of available SNNS functions Usage getSnnsRFunctionTable Value a data frame with columns name name of the function type the type of the function learning init update inParams the nu
46. mber of input parameters of the function outParams the number of output parameters of the function inputColumns Get the columns that are inputs Description This function extracts all columns from a matrix whose column names begin with in The example data of this package follows this naming convention Usage inputColumns patterns Arguments patterns matrix or data frame containing the patterns 26 Jordan jordan Create and train a Jordan network Description Jordan networks are partially recurrent networks and similar to Elman networks see elman Par tially recurrent networks are useful when working with time series data I e when the output of the network not only should depend on the current pattern but also on the patterns presented before Usage jordan x Default S3 method jordan x y size c 5 maxit 100 initFunc JE_Weights initFuncParams c 1 1 0 3 1 0 5 learnFunc JE_BP learnFuncParams c 0 2 updateFunc JE_Order updateFuncParams c 0 shufflePatterns FALSE linOut TRUE inputsTest NULL targetsTest NULL Arguments x a matrix with training inputs for the network additional function parameters currently not used y the corresponding targets values size number of units in the hidden layer s maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function
47. meters for the pruning function Unlike the other functions these have to be given in a named list See the pruning demos for further explanation Details There are a lot of different learning functions present in SNNS that can be used together with this function e g Std_Backpropagation BackpropBatch BackpropChunk BackpropMomentum BackpropWeightDecay Rprop Quickprop SCG scaled conjugate gradient Std_Backpropagation BackpropBatch e g have two parameters the learning rate and the max imum output difference The learning rate is usually a value between 0 1 and 1 It specifies the gradient descent step width The maximum difference defines how much difference between out put and target value is treated as zero error and not backpropagated This parameter is used to prevent overtraining For a complete list of the parameters of all the learning functions see the SNNS User Manual pp 67 The defaults that are set for initialization and update functions usually don t have to be changed Value an rsnns object References Rosenblatt F 1958 The perceptron A probabilistic model for information storage and organi zation in the brain Psychological Review 65 6 386 408 Rumelhart D E Clelland J L M amp Group P R 1986 Parallel distributed processing explo rations in the microstructure of cognition Mit Cambridge MA etc Zell A et al 1998 SNNS Stuttgart Neural Network Simulator Us
48. mmon network architecture in use Training is usually performed by error backpropagation or a related procedure Usage mlp x Default S3 method mlp x y size c 5 maxit 100 initFunc Randomize_Weights initFuncParams c 0 3 0 3 learnFunc Std_Backpropagation learnFuncParams c 0 2 0 updateFunc Topological_Order updateFuncParams c 0 hiddenActFunc Act_Logistic shufflePatterns TRUE linOut FALSE inputsTest NULL targetsTest NULL pruneFunc NULL pruneFuncParams NULL Arguments x a matrix with training inputs for the network additional function parameters currently not used y the corresponding targets values size number of units in the hidden layer s maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function hiddenActFunc the activation function of all hidden units shufflePatterns should the patterns be shuffled 30 mlp linOut sets the activation function of the output units to linear or logistic inputsTest a matrix with inputs to test the network targetsTest the corresponding targets for the test input pruneFunc the pruning function to use pruneFuncParams the para
49. mplementation by a call to RBF_Weights_Kohonen 0 0 0 0 0 anda successive call to the given initFunc usually RBF_Weights If this initialization doesn t fit your needs you should use the RSNNS low level interface to implement your own one Have a look then at the demos examples Also we note that depending on whether linear or logistic output is chosen the initialization parameters have to be different normally c 0 1 for linear and c 4 4 for logistic output Value an rsnns object References Poggio T amp Girosi F 1989 A Theory of Networks for Approximation and Learning A I Memo No 1140 C B I P Paper No 31 Technical report MIT ARTIFICIAL INTELLIGENCE LABORATORY Vogt M 1992 Implementierung und Anwendung von Generalized Radial Basis Functions in einem Simulator neuronaler Netze Master s thesis IPVR University of Stuttgart in German Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http ww ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German 38 rbfDDA Examples Not run demo rbf_irisSnnsR Not run demo rbf_sin Not run demo rbf_sinSnnsR inputs lt as matrix seq 10 0 1 outputs lt as matrix sin inputs runif inputsx x0 2 outputs lt normalizeData outputs 0_1 model lt rbf input
50. ncParams c 1 1 learnFuncParams c 0 5 mapX 2 0 8 0 8 mapX updateFuncParams c 0 0 1 shufflePatterns TRUE calculateMap TRUE calculateActMaps FALSE calculateSpanningTree FALSE saveWinnersPerPattern FALSE targets NULL Arguments x a matrix with training inputs for the network additional function parameters currently not used mapX the x dimension of the som mapY the y dimension of the som maxit maximum of iterations to learn initFuncParams the parameters for the initialization function learnFuncParams the parameters for the learning function updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled calculateMap should the som be calculated calculateActMaps should the activation maps be calculated calculateSpanningTree should the SNNS kernel algorithm for generating a spanning tree be applied saveWinnersPerPattern should a list with the winners for every pattern be saved targets optional target classes of the patterns Details As the computation of this function might be slow if many patterns are involved much of its output is made switchable see comments on return values Internally this function uses the initialization function Kohonen_Weights_v3 2 the learning func tion Kohonen and the update function Kohonen_Order of SNNS 64 Value an rsnns object special members map componentMaps actMaps som D
51. ng rates for the cases correctly uncorrectly classified and the number of cycles the net is trained before mean vectors are calculated A detailed description of the theory and the parameters is available as always from the SNNS documentation and the other referenced literature Value an rsnns object The fitted values member contains the activation patterns for all inputs References Kohonen T 1988 Self organization and associative memory Vol 8 Springer Verlag Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German Examples Not run demo dlvq_ziff Not run demo dlvq_ziffSnnsR data snnsData dataset lt snnsData dlvq_ziff_100 pat inputs lt dataset inputColumns dataset outputs lt dataset outputColumns dataset model lt dlvq inputs outputs fitted model outputs mean fitted model outputs elman Create and train an Elman network Description Elman networks are partially recurrent networks and similar to Jordan networks function jordan For details see explanations there 20 elman Usage elman x Default S3 method elman x y size c 5 maxit 100 initFunc JE_Weights initFuncParams c 1 1 0 3 1 0 5 learnFunc
52. nitial activation of context units Learning functions are JE_BP JE_BP_Momentum JE_Quickprop and JE_Rprop which are all adapted versions of their standard procedure counterparts Update functions that can be used are JE_Order and JE_Special A detailed description of the theory and the parameters is available as always from the SNNS documentation and the other referenced literature Value an rsnns object References Jordan M I 1986 Serial Order A Parallel Distributed Processing Approach Advances in Connectionist Theory Speech 121 ICS 8604 471 495 Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German See Also elman Examples Not run demo iris Not run demo laser Not run demo eight_elman Not run demo eight_elmanSnnsR data snnsData inputs lt snnsData laser_1000 pat inputColumns snnsData laser_100Q pat outputs lt snnsData laser_1000 pat outputColumns snnsData laser_1000 pat 28 matrixToActMapList patterns lt splitForTrainingAndTest inputs outputs ratio 0 15 modelJordan lt jordan patterns inputsTrain patterns targetsTrain size c 8 learnFuncParams c 0 1 maxit 100 inputsTest patterns inputsTest targetsTest patterns targetsTest lin
53. o the javaNNS the sucessor of SNNS from the original authors It makes the C core functionality available from a Java GUI Demos ending with SnnsR show the use of the low level api If you want to do special things with neural networks that are currently not implemented in the high level api you can see in this demos how to do it Many demos are present both as high level and low level versions The low level api consists mainly of the class SnnsR class which internally holds a pointer to a C object of the class SnnsCLib i e an instance of the SNNS kernel The class furthermore implements a calling mechanism for methods of the SnnsCLib object so that they can be called conveniently using the operator This calling mechanism also allows for transparent mask ing of methods or extending the kernel with new methods from within R See SnnsR method R functions that are added by RSNNS to the kernel are documented in this manual under topics be ginning with SnnsRObject Documentation of the original SNNS kernel user interface functions can be found in the SNNS User Manual 4 2 pp 290 314 A call to e g the SNNS kernel function krui_getNo0fUnits can be done with SnnsRObject getNoOfUnits However a few functions were excluded from the wrapping for various reasons Fur more details and other known issues see the file inst doc Knownlssues Another nice tool is the NeuralNetTools package that can be used to visualize and analyse t
54. onding predictions of a method for the targets 16 decodeClassLabels Details If the class labels are not already encoded they are encoded using encodeClassLabels with de fault values Value the confusion matrix decodeClassLabels Decode class labels to a binary matrix Description This method decodes class labels from a numerical or levels vector to a binary matrix 1 e it con verts the input vector to a binary matrix Usage decodeClassLabels x valTrue 1 valFalse 0 Arguments x class label vector valTrue see Details paragraph valFalse see Details paragraph Details In the matrix the value valTrue e g 1 is present exactly in the column given by the value in the input vector and the value valFalse e g 0 in the other columns The number of columns of the resulting matrix depends on the number of unique labels found in the vector E g the input c 1 3 2 3 will result in an output matrix with rows 100 001 010 001 Value a matrix containing the decoded class labels Author s The implementation is a slightly modified version of the function class ind from the nnet package of Brian Ripley References Venables W N and Ripley B D 2002 Modern Applied Statistics with S Springer Verlag denormalizeData 17 Examples decodeClassLabels c 1 3 2 3 decodeClassLabels c r b b r g g data iris decodeClassLabels iris 5 denormalizeData Revert data normalization
55. ory generates an rsnns object and initializes its member variables with the values given as parameters Furthermore it generates an object of SnnsR class Later this information is to be used to train the network Usage rsnnsObjectFactory subclass nInputs maxit initFunc initFuncParams learnFunc learnFuncParams updateFunc updateFuncParams shufflePatterns TRUE computeIterativeError TRUE pruneFunc NULL pruneFuncParams NULL 42 rsnnsObjectFactory Arguments subclass the subclass of rsnns to generate vector of strings nInputs the number of inputs the network will have maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled computeIterativeError should the error be computed in every iteration pruneFunc the pruning function to use pruneFuncParams the parameters for the pruning function Unlike the other functions these have to be given in a named list See the pruning demos for further explanation Details The typical procedure implemented in rsnns subclasses is the following generate the rsnns object with this object factory generate the network according to the archite
56. s outputs size 40 maxit 1000 initFuncParams c 0 1 0 0 01 0 01 learnFuncParams c 1e 8 0 le 8 0 1 0 8 lin0ut TRUE par mfrow c 2 1 plotIterativeError model plot inputs outputs lines inputs fitted model col green rbfDDA Create and train an RBF network with the DDA algorithm Description Create and train an RBF network with the dynamic decay adjustment DDA algorithm This type of network can only be used for classification The training typically begins with an empty network 1 e a network only consisting of input and output units and adds new units successively Itis a lot easier to use than normal RBF because it only requires two quite uncritical parameters Usage rbfDDA x Default S3 method rbfDDA x y maxit 1 initFunc Randomize_Weights initFuncParams c 0 3 0 3 learnFunc RBF DDA learnFuncParams c 0 4 0 2 5 updateFunc Topological_Order updateFuncParams c 0 shufflePatterns TRUE linOut FALSE Arguments x a matrix with training inputs for the network additional function parameters currently not used y the corresponding targets values maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function rbfDDA 39 learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use up
57. sCLib e g to do some parameter checking or postprocessing only a method with the same name but beginning with SnnsR__ has to be present in R See e g SnnsRObject initializeNet for such an implementation Error handling is also done within the method caller If the result of a function is a list with a member err then SnnsCLib__error is called to use the SNNS kernel function to get the corresponding error message code and an R warning is thrown containing this message Furthermore a serialization mechanism is implemented which all models present in the package use to be able to be saved and loaded by R s normal save load mechanism as RData files The completely trained object can be serialized with s lt snnsObject serializeNet RSNNS_untitled snnsObject variables serialization lt s serialization For the models implemented this is done in SnnsRObject train If the S4 object is then saved and loaded the calling mechanism will notice on the next use of a function that the pointer to the C SnnsCLib object is nil and if a serialization is present the object is restored from this serialization before the method is called SnnsRObject createNet Create a layered network Description This function creates a layered network in the given SnnsR object This is an SnnsR low level function You may want to have a look at SnnsR class to find out how to properly use it Usage S4 method for signature SnnsR createNet uni
58. snnsData 44 SnnsR class SnnsR class The main class of the package Description An S4 class that is the main class of RSNNS Each instance of this class contains a pointer to a C object of type SnnsCLib i e an instance of the SNNS kernel Details The only slot variables holds an environment with all member variables Currently there are two members constructed by the object factory snnsCLibPointer A pointer to the corresponding C object serialization a serialization of the C object in SNNS net format The member variables are not directly present as slots but wrapped in an environment to allow for changing the serialization by call by reference An object of this class is used internally by all the models in the package The object is always accessible by model snnsObject To make full use of the SNNS functionalities you might want to use this class directly Always use the object factory SnnsRObjectFactory to construct an object and the calling mechanism to call functions Through the calling mechanism many functions of SnnsCLib are present that are not documented here but in the SNNS User Manual So if you choose to use the low level interface it is highly recommended to have a look at the demos and at the SNNS User Manual References Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http
59. ta matrix parameters passed to image 34 plotRegressionError See Also vectorToActMap matrixToActMapList plotIterativeError Plot iterative errors of an rsnns object Description Plot the iterative training and test error of the net of this rsnns object Plot the iterative training and test error of the net of this rsnns object Usage plotIterativeError object S3 method for class rsnns plotIterativeError object Arguments object a rsnns object parameters passed to plot Details Plots if present the class members IterativeFitError as black line and IterativeTestError as red line plotRegressionError Plot a regression error plot Description The plot shows target values on the x axis and fitted predicted values on the y axis The optimal fit would yield a line through zero with gradient one This optimal line is shown in black color A linear fit to the actual data is shown in red color Usage plotRegressionError targets fits Arguments targets the target values fits the values predicted fitted by the model parameters passed to plot plotROC 35 plotROC Plot a ROC curve Description This function plots a receiver operating characteristic ROC curve Usage plotROC T D Arguments T predictions D targets parameters passed to plot Author s Code is taken from R news Volume 4 1 June 2004 References R news Volume 4 1 June 2004 pred
60. targetsTrain the corresponding targets initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function outputMethod the output method of the net maxit maximum of iterations to learn shufflePatterns should the patterns be shuffled computeError should the error be computed in every iteration inputsTest a matrix with inputs to test the network targetsTest the corresponding targets for the test input pruneFunc the pruning function to use pruneFuncParams the parameters for the pruning function Unlike the other functions these have to be given in a named list See the pruning demos for further explanation Value a list containing fitValues the fitted values i e outputs of the training inputs IterativeFitError The SSE in every iteration epoch on the training set testValues the predicted values i e outputs of the test inputs IterativeTestError The SSE in every iteration epoch on the test set 62 som SnnsRObject whereAreResults Get a list of output units of a net Description SnnsR low level function to get a list of output units of a net Usage HH S4 method for signature SnnsR whereAreResults outputMethod output gt Arguments outputMethod a string def
61. these could be ART1 ART2 or others However in SNNS ARTMAP is implemented for ARTI only So this function is to be used with binary input As explained in the description of art1 ART aims at solving the stability plasticity dilemma So the advantage of ARTMAP is that it is a supervised learning mechanism that guarantees stability Usage artmap x Default S3 method artmap x nInputsTrain nInputsTargets nUnitsRecLayerTrain nUnitsRecLayerTargets maxit 1 nRowInputsTrain 1 nRowInputsTargets 1 nRowUnitsRecLayerTrain 1 nRowUnitsRecLayerTargets 1 initFunc ARTMAP_Weights initFuncParams c 1 1 1 1 0 learnFunc ARTMAP learnFuncParams c 0 8 1 1 0 0 updateFunc ARTMAP_Stable updateFuncParams c 0 8 1 1 0 0 shufflePatterns TRUE 12 artmap Arguments x a matrix with training inputs and targets for the network additional function parameters currently not used nInputsTrain the number of columns of the matrix that are training input nInputsTargets the number of columns that are target values nUnitsRecLayerTrain number of units in the recognition layer of the training data ART network nUnitsRecLayerTargets number of units in the recognition layer of the target data ART network maxit maximum of iterations to perform nRowInputsTrain number of rows the training input units are to be organized in only for visual ization purposes of the net in the original SNNS software
62. thod for signature SnnsR resetRSNNS SnnsRObject setTTypeUnitsActFunc Set the activation function for all units of a certain ttype Description The function uses the function SnnsRObject getAllUnitsTType to find all units of a certain ttype and sets the activation function of all these units to the given activation function Usage S4 method for signature SnnsR setTTypeUnitsActFunc ttype act_func Arguments ttype a string containing the ttype act_func the name of the activation function to set See Also SnnsRObject getAllUnitsTType 58 SnnsRObject somPredictComponentMaps Examples Not run SnnsRObject setTTypeUnitsActFunc UNIT_HIDDEN Act_Logistic SnnsRObject setUnitDefaults Set the unit defaults Description This SnnsR low level function masks the SNNS kernel function of the same name to allow both for giving the parameters directly or as a vector If the second parameter bias is missing it is assumed that the first parameter should be interpreted as a vector containing all parameters Usage S4 method for signature SnnsR setUnitDefaults act bias st subnet_no layer_no act_func out_func Arguments act same as SNNS kernel function bias idem st idem subnet_no idem layer_no idem act_func idem out_func idem SnnsRObject somPredictComponentMaps Calculate the som component maps Description SnnsR low level function to calculate the som component maps Usag
63. tion of the theory and the parameters is available from the SNNS documentation and the other referenced literature assoz 13 Value an rsnns object The fitted values member of the object contains a list of two dimensional activation patterns References Carpenter G A Grossberg S amp Reynolds J H 1991 ARTMAP Supervised real time learning and classification of nonstationary data by a self organizing neural network Neural Networks 4 5 565 588 Grossberg S 1988 Adaptive pattern classification and universal recoding I parallel devel opment and coding of neural feature detectors MIT Press Cambridge MA USA chapter I pp 243 258 Herrmann K U 1992 ART Adaptive Resonance Theory Architekturen Implementierung und Anwendung Master s thesis IPVR University of Stuttgart in German Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German See Also arti art2 Examples Not run demo artmap_letters Not run demo artmap_lettersSnnsR data snnsData trainData lt snnsData artmap_train pat testData lt snnsData artmap_test pat model lt artmap trainData nInputsTrain 70 nInputsTargets 5 nUnitsRecLayerTrain 50 nUnitsRecLayerTargets 26 model fitted
64. ts is that the number of context units is not directly determined by the output dimension as in Jordan nets but by the number of hidden units which is more flexible as it is easy to add remove hidden units but not output units A detailed description of the theory and the parameters is available as always from the SNNS documentation and the other referenced literature encodeClassLabels 21 Value an rsnns object References Elman J L 1990 Finding structure in time Cognitive Science 14 2 179 211 Zell A et al 1998 SNNS Stuttgart Neural Network Simulator User Manual Version 4 2 IPVR University of Stuttgart and WSI University of T bingen http www ra cs uni tuebingen de SNNS Zell A 1994 Simulation Neuronaler Netze Addison Wesley in German See Also jordan Examples Not run demo iris Not run demo laser Not run demo eight_elman Not run demo eight_elmanSnnsR data snnsData inputs lt snnsData eight_016 patL inputColumns snnsData eight_016 pat outputs lt snnsData eight_016 pat outputColumns snnsData eight_Q16 pat par mfrow c 1 2 modelElman lt elman inputs outputs size 8 learnFuncParams c 0 1 maxit 1000 modelE1man modelJordan lt jordan inputs outputs size 8 learnFuncParams c 0 1 maxit 1000 model Jordan plotIterativeError modelElman plotIterativeError model Jordan summary modelE1man summary model Jordan
65. tsPerLayer fullyConnectedFeedForward TRUE iNames NULL oNames NULL Arguments unitsPerLayer a vector of integers that represents the number of units in each layer including input and output layer fullyConnectedFeedForward if TRUE the network is fully connected as a feed forward network If FALSE no connections are created iNames names of input units oNames names of output units See Also SnnsR class 48 SnnsRObject extractNetInfo Examples obj1 lt SnnsRObjectFactory objl createNet c 2 2 FALSE obj1 getUnitDefinitions obj2 lt SnnsRObjectFactory obj2 createNet c 8 5 5 2 TRUE obj2 getUnitDefinitions SnnsRObject createPatSet Create a pattern set Description SnnsR low level function to create a pattern set in the SNNS kernel from the values given so that they are available in the SNNS kernel for use Usage S4 method for signature SnnsR createPatSet inputs targets Arguments inputs the input values targets the target values Value a list with elements err and set_no The latter one identifies the pattern set within the SnnsR class object SnnsRObject extractNetInfo Get characteristics of the network Description The returned list has three members e infoHeader general information about the network unitDefinitions information about the units e fullWeightMatrix weight matrix of the connections SnnsRObject extractPatterns 49 Usage S4 method for signature
66. vector Usage toNumericClassLabels x Arguments x inputs train 67 Value the vector converted to a numeric vector Examples data iris toNumericClassLabels iris 5 train Internal generic train function for rsnns objects Description The function calls SnnsRObject train and saves the result in the current rsnns object This function is used internally by the models e g mlp for training Unless you are not about to implement a new model on the S3 layer you most probably don t want to use this function Internal generic train function for rsnns objects Usage train object S3 method for class rsnns train object inputsTrain targetsTrain NULL inputsTest NULL targetsTest NULL serializeTrainedObject TRUE Arguments object the rsnns object additional function parameters currently not used inputsTrain training input targetsTrain training targets inputsTest test input targetsTest test targets serializeTrainedObject parameter passed to SnnsRObject train Value an rsnns object to which the results of training have been added 68 weightMatrix vectorToActMap Convert a vector to an activation map Description Organize network activation as 2d map Usage vectorToActMap v nrow 0 ncol 0 Arguments V the vector containing the activation pattern nrow number of rows the resulting matrices will have ncol number of columns the resulting matrices will hav
67. voting of the class labels for the final label of the unit 60 SnnsRObject train See Also som SnnsRObject somPredictCurrPatSetWinnersSpanTree Get the spanning tree of the SOM Description SnnsR low level function to get the spanning tree of the SOM This function calls directly the corresponding SNNS kernel function the only one available for SOM Advantage are faster com putation disadvantage is somewhat limited information in the output Usage S4 method for signature SnnsR somPredictCurrPatSetWinnersSpanTree Value the spanning tree which is the som showing for each unit a number identifying the last pattern for which this unit won We note that also if there are more than one patterns only the last one is saved See Also som SnnsRObject train Train a network and test it in every training iteration Description SnnsR low level function to train a network and test it in every training iteration Usage S4 method for signature SnnsR train inputsTrain targetsTrain NULL initFunc Randomize_Weights initFuncParams c 1 0 1 0 learnFunc Std_Backpropagation learnFuncParams c 0 2 0 updateFunc Topological_Order updateFuncParams c 0 0 outputMethod reg_class maxit 100 shufflePatterns TRUE computeError TRUE inputsTest NULL targetsTest NULL pruneFunc NULL pruneFuncParams NULL SnnsRObject train 61 Arguments inputsTrain a matrix with inputs for the network
68. want to have a look at SnnsR class to find out how to properly use it Usage S4 method for signature SnnsR getAllUnitsTType ttype Arguments ttype a string containing the ttype Value a vector with integer numbers identifying the units See Also SnnsRObject getAllOutputUnits SnnsRObject getAllInputUnits SnnsRObject getAllHiddenUnits SnnsRObject getCompleteWeightMatrix Get the complete weight matrix Description Get a weight matrix containing all weights of all neurons present in the net Usage S4 method for signature SnnsR getCompleteWeightMatrix setDimNames Arguments setDimNames indicates whether names of units are extracted and set as row col names in the weight matrix SnnsRObject getInfoHeader 53 Value the complete weight matrix SnnsRObject getInfoHeader Get an info header of the network Description Get an info header of the network Usage S4 method for signature SnnsR getInfoHeader Value a data frame containing some general characteristics of the network SnnsRObject getSiteDefinitions Get the sites definitions of the network Description Get the sites definitions of the network Usage S4 method for signature SnnsR getSiteDefinitions Value a data frame containing information about all sites present in the network 54 SnnsRObject getUnitDetinitions SnnsRObject getTypeDefinitions Get the F Type definitions of the network
69. wo sets of neurons 56 SnnsRObject predictCurrPatSet See Also SnnsRObject getAllUnitsTType SnnsRObject initializeNet Initialize the network Description This SnnsR low level function masks the SNNS kernel function of the same name to allow for both giving the initialization function directly in the call or to use the one that is currently set Usage S4 method for signature SnnsR initializeNet parameterInArray initFunc Arguments parameterInArray the parameters of the initialization function initFunc the name of the initialization function SnnsRObject predictCurrPatSet Predict values with a trained net Description SnnsR low level function to predict values with a trained net Usage S4 method for signature SnnsR predictCurrPatSet outputMethod reg_class updateFuncParams c 0 0 Arguments outputMethod is passed to SnnsRObject whereAreResults updateFuncParams parameters passed to the networks update function SnnsRObject resetRSNNS 7 Details This function has to be used embedded in a step of loading and afterwards removing the patterns into the SnnsR class object As SNNS only supports 2 pattern sets in parallel removing unneeded pattern sets is quite important Value the predicted values SnnsRObject resetRSNNS Reset the SnnsR object Description SnnsR low level function to delete all pattern sets and delete the current net in the SnnsR class object Usage S4 me
70. y the corresponding targets values size number of units in the hidden layer s rbf 37 maxit maximum of iterations to learn initFunc the initialization function to use initFuncParams the parameters for the initialization function learnFunc the learning function to use learnFuncParams the parameters for the learning function updateFunc the update function to use updateFuncParams the parameters for the update function shufflePatterns should the patterns be shuffled linOut sets the activation function of the output units to linear or logistic inputsTest a matrix with inputs to test the network targetsTest the corresponding targets for the test input Details RBF networks are feed forward networks with one hidden layer Their activation is not sigmoid as in MLP but radially symmetric often gaussian Thereby information is represented locally in the network in contrast to MLP where it is globally represented Advantages of RBF networks in comparison to MLPs are mainly that the networks are more interpretable training ought to be easier and faster and the network only activates in areas of the feature space where it was actually trained and has therewith the possibility to indicate that it just doesn t know Initialization of an RBF network can be difficult and require prior knowledge Before use of this function you might want to read pp 172 183 of the SNNS User Manual 4 2 The initialization is performed in the current i
71. zation Description The input matrix is column wise normalized Usage normalizeData x type norm Arguments x input data type either type string specifying the type of normalization Implemented are 0_1 center and norm or attribute list of a former call to this method to apply e g normalization of the training data to the test data 32 normTrainingAndTestSet Details The parameter type specifies how normalization takes place 0_1 values are normalized to the 0 1 interval The minimum in the data is mapped to zero the maximum to one center the data is centered 1 e the mean is substracted norm the data is normalized to mean zero variance one Value column wise normalized input The normalization parameters that were used for the normalization are present as attributes of the output They can be obtained with getNormParameters See Also denormalizeData getNormParameters normTrainingAndTestSet Function to normalize training and test set Description Normalize training and test set as obtained by splitForTrainingAndTest in the following way The inputsTrain member is normalized using normalizeData with the parameters given in type The normalization parameters obtained during this normalization are then used to normalize the inputsTest member if dontNormTargets is not set then the targets are normalized in the same way In classification problems normalizing the targets normally makes no s

Package `RSNNS`

Contents

Download Pdf Manuals

Related Search

Related Contents