O'Reilly logo

Java Deep Learning Projects by Md. Rezaul Karim

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Multilayer perceptron network construction

As I informed you in the preceding chapter, DL4J-based neural networks are made of multiple layers. Everything starts with a MultiLayerConfiguration, which organizes those layers and their hyperparameters.

Hyperparameters are a set of variables that determine how a neural network would learn. There are many parameters, for example, how many times and how often to update the weights of the model (called an epoch), how to initialize network weights, which activation function to be used, which updater and optimization algorithms to be used, the learning rate (that is, how fast the model should learn), how many hidden layers are there, how many neurons are there in each layer, and so on.

We now create ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required