Restricted Boltzmann machine associative memory

Koki Nagatani, Masafumi Hagiwara

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

Restricted Boltzmann machine associative memory (RBMAM) is proposed in this paper. RBMAM memorizes patterns using contrastive divergence learning procedure. It recalls by calculating the reconstruction of pattern using conditional probability. In order to examine the performance of the proposed RBMAM, extensive computer simulations have been carried out. As the result, it has shown that the performance of RBMAM is overwhelming compared with the conventional neural network associative memories. For example as for storage capacity, RBMAM can store about from 2Nhidden to ANhideen patterns, where Nhidden denotes the number of neurons in the hidden layer. Similarly we have obtained superior performance of RBMAM in respect of noise tolerance and pattern complement.

本文言語English
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3745-3750
ページ数6
ISBN(電子版)9781479914845
DOI
出版ステータスPublished - 2014 9月 3
イベント2014 International Joint Conference on Neural Networks, IJCNN 2014 - Beijing, China
継続期間: 2014 7月 62014 7月 11

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks

Other

Other2014 International Joint Conference on Neural Networks, IJCNN 2014
国/地域China
CityBeijing
Period14/7/614/7/11

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Restricted Boltzmann machine associative memory」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル