Neural Network Model of the Backpropagation Algorithm

We apply a neural network to model neural network learning algorithm itself. The process of weights updating in neural network is observed and stored into file. Later, this data is used to train another network, which then will be able to train neural networks by imitating the trained algorithm. We use backpropagation algorithm for both, for training, and for sampling the training process. We imitate the training of the network as whole. All the weights and weight changes of multilayer neural network are processed in parallel in order to model mutual dependencies between weights. Experimental results are provided.