期刊
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
卷 18, 期 2, 页码 135-145出版社
WORLD SCIENTIFIC PUBL CO PTE LTD
DOI: 10.1142/S0129065708001440
关键词
quaternion; Hopfield neural network; associative memory; multiplet
Associative memory networks based on quaternionic Hopfield neural network are investigated in this paper. These networks are composed of quaternionic neurons, and input, output, threshold, and connection weights are represented in quaternions, which is a class of hypercomplex number systems. The energy function of the network and the Hebbian rule for embedding patterns are introduced. The stable states and their basins are explored for the networks with three neurons and four neurons. It is clarified that there exist at most 16 stable states, called multiplet components, as the degenerated stored patterns, and each of these states has its basin in the quaternionic networks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据