Layers is null for a MultiLayerNetwork object

I’ve defined the following MultiLayerNetwork for an intent detection scenario (for a given user input I want to predict the intent that corresponds to that input). I’m trying to define a network with three layers: an embedding one for a BagOfWords (created from the training sentences in the intents definition), a hidden one and a final output one that returns the matching probabilities for every intent.

Two questions:

  • Is there obviously wrong in my attempted architecture?
  • When I create the model from this configuration, I don’t get any type of exception but the “layers” attribute is null (the model object itself is not)

See below the code I’m using. Thanks!

  int numOutputs = context.numberIntents();
        int vocabSize = context.getBagOfWords().getVocabCache().numWords();

        MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
                .updater(new Nesterovs(0.01, 0.9))
                .layer(new EmbeddingLayer.Builder().nIn(vocabSize).nOut(24)
                .layer(new DenseLayer.Builder().nIn(24).nOut(8)
                .layer(new OutputLayer.Builder((LossFunctions.LossFunction.NEGATIVELOGLIKELIHOOD))  

        MultiLayerNetwork model = new MultiLayerNetwork((conf));