Build and train Artifical Neural Network of any depth in a single line code. Choose the hyperparameters to improve the accuracy or generalisation of model.
deepnet( x, y, hiddenLayerUnits = c(2, 2), activation = c("sigmoid", "relu"), reluLeak = 0, modelType = c("regress"), iterations = 500, eta = 10^-2, seed = 2, gradientClip = 0.8, regularisePar = 0, optimiser = "adam", parMomentum = 0.9, inputSizeImpact = 1, parRmsPropZeroAdjust = 10^-8, parRmsProp = 0.9999, printItrSize = 100, showProgress = T, stopError = 0.01, miniBatchSize = NA, useBatchProgress = T, ignoreNAerror = F )
| x | a data frame with input variables |
|---|---|
| y | a data frame with ouptut variable |
| hiddenLayerUnits | a numeric vector, length of vector indicates number of hidden layers and each element in vector indicates corresponding hidden units Eg: c(6,4) for two layers, one with 6 hiiden units and other with 4 hidden units. Note: Output layer is automatically created. |
| activation | one of "sigmoid","relu","sin","cos","none". The default is "sigmoid". Choose a activation per hidden layer |
| reluLeak | numeric. Applicable when activation is "relu". Specify value between 0 any number close to zero below 1. Eg: 0.01,0.001 etc |
| modelType | one of "regress","binary","multiClass". "regress" for regression will create a linear single unit output layer. "binary" will create a single unit sigmoid activated layer. "multiClass" will create layer with units corresponding to number of output classes with softmax activation. |
| iterations | integer. This indicates number of iteratios or epochs in backpropagtion .The default value is 500. |
| eta | numeric.Hyperparameter,sets the Learning rate for backpropagation. Eta determines the convergence ability and speed of convergence. |
| seed | numeric. Set seed with this parameter. Incase of sin activation sometimes changing seed can yeild better results. Default is 2 |
| gradientClip | numeric. Hyperparameter numeric value which limits gradient size for weight update operation in backpropagation. Default is 0.8 . It can take any postive value. |
| regularisePar | numeric. L2 Regularisation Parameter . |
| optimiser | one of "gradientDescent","momentum","rmsProp","adam". Default value "adam" |
| parMomentum | numeric. Applicable for optimiser "mometum" and "adam" |
| inputSizeImpact | numeric. Adjusts the gradient size by factor of percentage of rows in input. For very small data set setting this to 0 could yeild faster result. Default is 1. |
| parRmsPropZeroAdjust | numeric. Applicable for optimiser "rmsProp" and "adam" |
| parRmsProp | numeric.Applicable for optimiser "rmsProp" and "adam" |
| printItrSize | numeric. Number of iterations after which progress message should be shown. Default value 100 and for iterations below 100 atleast 5 messages will be seen |
| showProgress | logical. True will show progress and F will not show progress |
| stopError | Numeric. Rmse at which iterations can be stopped. Default is 0.01, can be set as NA in case all iterations needs to run. |
| miniBatchSize | integer. Set the mini batch size for mini batch gradient |
| useBatchProgress | logical. Applicable for miniBatch , setting T will use show rmse in Batch and F will show error on full dataset. For large dataset set T |
| ignoreNAerror | logical. Set T if iteration needs to be stopped when predictions become NA |
returns model object which can be passed into predict.deepnet
require(deepdive) x <- data.frame(a = runif(10),b = runif(10)) y<- data.frame(y=20*x$a +30*x$b+10) #train modelnet<-deepnet(x,y,c(2,2), activation = c('relu',"sigmoid"), reluLeak = 0.01, modelType = "regress", iterations =5, eta=0.8, optimiser="adam")#>#>#>#>#>#predict predDeepNet<-predict.deepnet(modelnet,newData=x) #evaluate sqrt(mean((predDeepNet$ypred-y$y)^2))#> [1] 21.73252