January 2018
Intermediate to advanced
470 pages
11h 9m
English
Now, let's define the internal neural network structure and hyperparameters for the LSTM network:
val nHidden = 128 // Number of features in a hidden layer val nClasses = 6 // Total classes to be predicted val learningRate = 0.001f val trainingIters = trainingDataCount * 100 // iterate 100 times on trainset: total 7352000 iterations val batchSize = 1500 val displayIter = 15000 // To show test set accuracy during training val numLstmLayer = 3
Read now
Unlock full access