Training Java Resilient Propagation

Resilient Propagation is one of the fastest training algorithms available for Encog. Resilient propagation is a supervised learning method. It works similarly to Backpropagation, except that an individual delta is calculated for each connection. These delta values are gradually changed until the neural network weight matrix converges on a potentially ideal weight matrix. Resilient propagation allows several parameters to be set, but it is rare that these training parameters need to be changed beyond their default values. Resilient propagation can be used with feedforward and simple recurrent neural networks.