Understanding static neural networks
Static neural networks are ANNs that undergo a training or learning phase and then do not change when they are used. They differ from dynamic neural networks, which learn constantly and may undergo structural changes after the initial training period. Static neural networks are useful when the results of a model are relatively easy to reproduce or are more predictable. We will look at dynamic neural networks in a moment, but we will begin by creating our own basic static neural network.
A basic Java example
Before we examine various libraries and tools available for constructing neural networks, we will implement our own basic neural network using standard Java libraries. The next example is an adaptation of work done by Jeff Heaton (http://www.informit.com/articles/article.aspx?p=30596). We will construct a feed-forward backpropagation neural network and train it to recognize the XOR operator pattern. Here is the basic truth table for XOR:
X | Y | Result |
|
|
|
|
|
