Search. Read. Cite.

Easy to search. Easy to read. Easy to cite with credible sources.

Information Technology Journal

Year: 2008  |  Volume: 7  |  Issue: 4  |  Page No.: 684 - 688

Study on the Capacity of Hopfield Neural Networks

Humayun Karim Sulehria and Ye Zhang

Abstract

Hopfield Neural Networks (HNNs) are an important class of neural networks that are useful in pattern recognition and the capacity is an important criterion for such a network design. In this research, we study the capacity experimentally determined by Hopfield and also highlight the upper and (lower) bounds on it. Improvements in the capacity are also determined as well as the methods for achieving the higher capacity. HNN capacity enhancements and refinements may also inspire other models.

Cited References Fulltext