Weighted bipolar neural network with high-capacity stable storage

Donghui Guo, Zhenxiang Chen, Ruitang Liu, Boxi WuProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 1994 · DOI

Abstract

In this paper, a bipolar neural network of weighted neurons' connection T<SUB>ij</SUB> was presented, based on the system energy evolution in neural networks dynamic course. The weighted connection matrix T<SUB>ij</SUB> consists of a monotone increasing even function f(z), which makes every stored patterns as the stable attractors of network system.
BibTeX
@inproceedings{guo1994weighted,
  author = {Donghui Guo and Zhenxiang Chen and Ruitang Liu and Boxi Wu},
  title = {{Weighted bipolar neural network with high-capacity stable storage}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {1994},
  doi = {10.1117/12.182097},
}

Loading related content...

Figure