Title :
An error correcting algorithm for Hopfield network
Author :
Hui, Chi-Chung ; Chan, Lai-Wan
Author_Institution :
Dept. of Comput Sci., Chinese Univ. of Hong Kong, Shatin, Hong Kong
Abstract :
The principle and the weakness of the Hopfield network are discussed. It is found that the assumption that the Hopfield network made on the noise effect of input patterns is inappropriate and an adaptive training algorithm that minimizes the noise effect of the input patterns is presented. This algorithm alters the connection weights of the network. It is shown that the storage capacity of the resultant model increases from 0.16n to greater than 1.14n, where n is the number of neurons in the network. Moreover, the model has a higher error tolerance level than the original model
Keywords :
Hopfield neural nets; error correction; learning (artificial intelligence); Hopfield network; adaptive training algorithm; connection weights; error correcting algorithm; error tolerance level; input patterns; neurons; noise effect; storage capacity; Adaptive algorithm; Computer errors; Computer science; Equations; Error correction; Neurons; Random number generation; Test pattern generators; Testing;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287069
