Year: 2004
Type: conference-paper
Abstract: Hopfield type associative memory networks usually use a bipolar representation.It is also possible to use a binary 0/1 representation, although in the standard model this lowers performance.This paper reports an empirical investigation into the performance of both binary and bipolar associative memories, trained using the simple perceptron learning rule.Such networks normally have much better performance than the standard model.It is found that the binary networks perform just as well as the bipolar networks, although they take significantly longer to train.
Authors: N. Davey, R. Frank, Stephen P. Hunt, R.G. Adams, Lee Calcraft
Institution: University of Hertfordshire
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W752259063