Neural network training method

摘要

The method involves using training data consisting of at least one input value (EWi, i = 1.. n) and at least one target value (ZW) associated with the input value (Ewi), for training a neural network (NN). The input value is supplied to neurons (NES) of an input layer (ES) for the training of the neural of network. A weighted result signal of a neuron of the input layer is supplied to exactly one neuron (NZES) of an intermediate input layer (ZES). The neurons of the intermediate input layer and the weights of the connections between a neuron of the input layer and a neuron of the intermediate input layer are respectively considered during the training. The training data contains pref. at least one intermediate target value (ZZW), which is considered during the training, and from which the target value is formed.