1. Define the neural network configuration using MultiLayerConfiguration:

MultiLayerConfiguration.Builder builder = new NeuralNetConfiguration.Builder().weightInit(WeightInit.RELU_UNIFORM)
 .updater(new Adam(0.015D))
 .list();
 

2. Define the input layer configuration using DenseLayer:

builder.layer(new DenseLayer.Builder().nIn(incomingConnectionCount).nOut(outgoingConnectionCount).activation(Activation.RELU)
.build())
.build();