HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
工学研究科  >
雑誌発表論文等  >

Storage capacity of two-dimensional neural networks

PRE65-1.pdf96.46 kBPDF見る/開く

タイトル: Storage capacity of two-dimensional neural networks
著者: Koyama, Shinsuke 著作を一覧する
発行日: 2001年12月
出版者: American Physical Society
誌名: Physical Review E
巻: 65
号: 1
開始ページ: 016124
出版社 DOI: 10.1103/PhysRevE.65.016124
抄録: We investigate the maximum number of embedded patterns in the two-dimensional Hopfield model. The grand state energies of two specific network states, namely, the energies of the pure-ferromagnetic state and the state of specific one stored pattern are calculated exactly in terms of the correlation function of the ferromagnetic Ising model. We also investigate the energy landscape around them and the stability of the pure retrieval state. Taking into account the qualitative features of the phase diagrams obtained by Nishimori, Whyte, and Sherrington [Phys. Rev. E 51, 3628 (1995)], we conclude that the network cannot retrieve more than three patterns.
Rights: Copyright © 2001 American Physical Society
資料タイプ: article
出現コレクション:雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

提供者: 小山 慎介


本サイトに関するご意見・お問い合わせは repo at へお願いします。 - 北海道大学