AN IMPROVED METHOD AND SYSTEM FOR TRAINING AN ARTIFICIAL NEURAL NETWORK

摘要

A method and system for training an artificial neural network ('ANN') (10) are disclosed. One embodiment of the method initializes an ANN (10) by assigning values to one or more weights. An adaptive learning rate is set to an initial starting value and training patterns for an input layer (18) and an output layer (22) are stored. The input layer training pattern is processed in the ANN (10) to obtain an output pattern. An error is calculated between the output layer training pattern and the output pattern and used to calculate an error ratio, which is used to adjust the value of the adaptive learning rate. If the error ratio is less than a threshold value, the adaptive learning rate can be multiplied by a step-up factor to increase the learning rate. If the error ratio is greater than the threshold value, the adaptive learning rate can be multiplied by a step-down factor to reduce the learning rate. The value of the weights used to initialize the ANN (10) are adjusted based on the calculated error and the adaptive learning rate. The training method is repeated until the ANN (10) achieves a final trained state.