Pour plus de détails : Tech4j on Youtube
C'est un framwork de deeplearning :
- Configuration
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.optimizationAlgo(OptimizationAlgorithm.STOCHASTIC_GRADIENT_DESCENT)
.updater(new Nesterovs(learningRate, 0.9))
.list(
new DenseLayer.Builder().nIn(numInputs).nOut(numHiddenNodes)
.activation("relu").build(),
new OutputLayer.Builder(LossFunction.NEGATIVELOGLIKELIHOOD)
.activation("softmax").nIn(numHiddenNodes).nOut(numOutputs)
.build())
.backprop(true).build();
MultiLayerNetwork model = new MultiLayerNetwork(conf);
- Entrainement
model.fit(trainSet);// single epoch
ou bien
for (int i=0; i< numberOfEpoc; i++){
model.fit(trainSet);
}
- Evaluation des performences
- Monotoring / Troubleshooting
ScoreIterationListener
HistogramIterationListener