Acceleration for both Boltzmann Machine Learning and Mean Field Theory Learning

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

This paper proposes new learning algorithms for both the Boltzmann Machine (BM) learning and the Mean Field Theory (MFT) learning to accelerate their learning speeds. The derivation of the new algorithms are based on the following assumptions: 1) The alternative cost function is {equation presented} where G τis the information-theoretical measure at the learning epoch τ, not G which is the commonly used information-theoretical measure in the derivation of BM learning. 2) The most recent weights are assumed in calculating Gn, which technique is used in the derivation of Recursive Least-Squares (RLS) algorithm. As a result, momentum terms which accelerate learning can be derived in the BM and the MFT learning algorithms. Comparing the proposed MFT learning algorithm with the conventional MFT algorithm by computer simulation, we show the effectiveness of the proposed method.

本文言語English
ホスト出版物のタイトルProceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
出版社Institute of Electrical and Electronics Engineers Inc.
ページ687-692
ページ数6
ISBN(電子版)0780305590
DOI
出版ステータスPublished - 1992
イベント1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States
継続期間: 1992 6月 71992 6月 11

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks
1

Conference

Conference1992 International Joint Conference on Neural Networks, IJCNN 1992
国/地域United States
CityBaltimore
Period92/6/792/6/11

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Acceleration for both Boltzmann Machine Learning and Mean Field Theory Learning」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