Constructing associative memories using high-order neural networks

研究成果: 雜誌貢獻期刊論文同行評審

摘要

A class of neural network for constructing associative memories that learn the memory patterns as well as their neighbouring patterns is presented. The network is basically a layer of perceptrons with high-order polynomials as their discriminant functions. A learning algorithm is proposed for the network to learn arbitrary bipolar patterns. The simulation results show that the associative memories implemented in this way achieve a set of desirable characteristics, namely high storage capacity, nearest convergence, and existence of a ‘no decision’ state which attracts indistinguishable inputs. Furthermore, it is also possible to shape the attraction basin of a memory pattern under any metrics definition of distance.

原文英語
頁(從 - 到)1122-1124
頁數3
期刊Electronics Letters
28
發行號12
DOIs
出版狀態已發佈 - 1992 六月 4

ASJC Scopus subject areas

  • 電氣與電子工程

指紋

深入研究「Constructing associative memories using high-order neural networks」主題。共同形成了獨特的指紋。

引用此