Chaotic multidirectional associative memory

Chaotic multidirectional associative memory
复制标题

混沌多向联想记忆

DOI:
10.1109/icnn.1997.616205
复制
发表时间:
1997
期刊:
Proceedings of International Conference on Neural Networks (ICNN'97)
影响因子:
--
通讯作者:
M. Hagiwara
M. Hagiwara
中科院分区:
--
文献类型:
--
作者:
Y. Osana;M. Hattori;M. Hagiwara

文献摘要

被引文献

相似文献

提出了一种混沌多向联想记忆(CMAM),并进行了仿真。它可以处理多对多的关联,结构非常简单。此外,在CMAM的关联中观察到与心理事实(启动效应)的相似性。为了实现多对多关联,CMAM将每个训练数据与其自身的上下文信息一起存储,并采用混沌神经元。由于混沌神经元通过混沌改变其状态,因此CMAM可以实现多对多的联想。
A chaotic multidirectional associative memory (CMAM) is proposed and simulated. It can deal with many-to-many associations and the structure is very simple. Furthermore, similarity to a psychological fact (priming effect) is observed in the association of the CMAM. In order to enable many-to-many associations, the CMAM memorizes each training data together with its own contextual information and employs chaotic neurons. Since the chaotic neurons change their states by chaos, many-to-many associations can be realized in the CMAM.