WEKO3
インデックスリンク
アイテム
Probabilistic memory capacity of recurrent neural networks
http://hdl.handle.net/2297/6790
http://hdl.handle.net/2297/679073a6a0bf-e529-48d0-989f-e2affdf2abc9
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
TE-PR-NAKAYAMA-K-1291.pdf (748.1 kB)
|
|
| Item type | 会議発表論文 / Conference Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2017-10-03 | |||||
| タイトル | ||||||
| タイトル | Probabilistic memory capacity of recurrent neural networks | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
| 資源タイプ | conference paper | |||||
| 著者 |
Miyoshi, Seiji
× Miyoshi, Seiji× Nakayama, Kenji |
|||||
| 提供者所属 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | 金沢大学理工研究域電子情報学系 | |||||
| 書誌情報 |
IEEE International Conference on Neural Networks - Conference Proceedings 巻 2, p. 1291-1296, 発行日 1996-06-01 |
|||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 1098-7576 | |||||
| 出版者 | ||||||
| 出版者 | IEEE(Institute of Electrical and Electronics Engineers) | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | In this paper, probabilistic memory capacity of recurrent neural networks(RNNs) is investigated. This probabilistic capacity is determined uniquely if the network architecture and the number of patterns to be memorized are fixed. It is independent from a learning method and the network dynamics. It provides the upper bound of the memory capacity by any learning algorithms in memorizing random patterns. It is assumed that the network consists of N units, which take two states. Thus, the total number of patterns is the Nth power of 2. The probabilities are obtained by discriminations whether the connection weights, which can store random M patterns at equilibrium states, exist or not. A theoretical way for this purpose is derived, and actual calculation is executed by the Monte Carlo method. The probabilistic memory capacity is very important in applying the RNNs to real fields, and in evaluating goodness of learning algorithms. As an example of a learning algorithm, the improved error correction learning is investigated, and its convergence probabilities are compared with the upper bound. A linear programming method can be effectively applied to this numerical analysis. | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
