On binary associative memories based on recurrent neural networks
作者:
Tzi‐Dar Chiueh,
期刊:
Journal of the Chinese Institute of Engineers
(Taylor Available online 1994)
卷期:
Volume 17,
issue 1
页码: 55-62
ISSN:0253-3839
年代: 1994
DOI:10.1080/02533839.1994.9677567
出版商: Taylor & Francis Group
关键词: associative memory;neural network
数据来源: Taylor
摘要:
Associative memory has been one of the focal points in recent neural network research. In this paper, we propose a general model for binary associative memories based on a recurrent network structure. The proposed model is based on an evolution process that is similar to the political election process. The essence of the new model lies in theweighting Junctionsand how the system evolves according to the combined, weighted contribution from all stored patterns. With appropriate choice of weighting functions, new and efficient binary associative memories can be developed quite easily. The model therefore provides a solid foundation for the design of binary associative memories suitable for future electronic and optical technology. Furthermore, many well‐known neural associative memories are shown to be special cases of this new model with appropriate reformulation of their respective evolution equation. The stability, hardware complexity, and storage capacity issues of these associative memories are also discussed.
点击下载:
PDF (651KB)
返 回