Training Java Backpropagation

Backpropagation is one of the oldest training techniques for feedforward and simple recurrent neural networks. It is a supervised learning method, and is an implementation of the Delta rule. The term is an abbreviation for "backwards propagation of errors\. Backpropagation requires that the activation function used by the layers is differentiable. For most training situations where backpropagation could be applied, resilient propagation is a better solution.