Neural networks and method for training neural networks

摘要

Methods (30) for training an artificial neural network (NN) are disclosed. An example method (30) includes: initializing the NN by selecting an output of the NN to be trained and connecting an output neuron of the NN to input neuron(s) in an input layer of the NN for the selected output; preparing a data set to be learnt by the NN; and, applying the prepared data set to the NN to be learnt by applying an input vector of the prepared data set to the first hidden layer of the NN, or the output layer of the NN if the NN has no hidden layer(s), and determining whether at least one neuron for the selected output in each layer of the NN can learn to produce the associated output for the input vector.

主权项

1. An artificial neural network, implemented on one or more computers, comprising a plurality of neurons arranged in layers, the artificial neural network being arranged to receive a new neuron into a layer of the artificial neural network during training, the new neuron being added to the neural network when no other neuron in that layer for a selected output can learn a relationship associated with an input vector of a data set being learnt, wherein:
the new neuron being updated with both the relationship which could not be learnt by any other neuron in that layer and a modified data set from a last trained neuron in that layer that contributes to the selected output of the neural network, wherein the modified data set is formed by copying all learnt relationships from the last trained neuron into the new neuron and modifying the copied relationship based upon the relationship which could not be learnt by any other neuron in that layer; and, one or more output neurons being updated to accept input from the new neuron.