| アイテムタイプ |
default_学術雑誌論文 / Journal Article(1) |
| タイトル |
|
|
タイトル |
Unlearning of Mixed States in the Hopfield Model : Finite Loading Case |
|
言語 |
en |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
Hopfield model |
| キーワード |
|
|
言語 |
en |
|
主題Scheme |
Other |
|
主題 |
unlearning of mixed states |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 著者 |
大谷,遥
吉田,緑
清川,修二
上江洌,達也
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
We study the unlearning of mixed states in the Hopfield model for the finite loading case, that is, α = p/N ≪ 1, where N and p are the numbers of neurons and embedded patterns, respectively. In the general situation that any number of mixed states that exist in the model is unlearned, we derive the saddle point equations (SPEs) and evolution equations for overlaps by introducing sublattices. We postulate a condition that the solutions are stable in equilibrium, and prove that the static and dynamic stabilities are the same. We also prove that the stable state of the Hopfield model continuously changes and is statically and dynamically stable for sufficiently small unlearning coefficients. For p = 3, we perform detailed theoretical and numerical calculations. In the case that a single mixed state is unlearned, we determine phase boundaries using the Hessian matrix and by numerically integrating evolution equations. We performed Markov chain Monte Carlo simulations and find that the simulation results agree with the theoretical ones reasonably well. For general p, when all of the mixed states are unlearned with an equal unlearning coefficient η, we derive the formulae for critical unlearning coefficients at the temperature T = 0 below which embedded patterns and mixed states exist and are stable as solutions of the SPEs. We found that there is an unlearning region of (T,η) in which all patterns are retained and all mixed states are deleted, although tuning the parameters in this region is more difficult as p increases since the region shrinks. We numerically confirmed the theoretical results of the p dependences of the critical unlearning coefficients. |
|
言語 |
en |
| 内容記述 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
本論文の著作権は一般社団法人日本物理学会(The Physical Society of Japan)が保有しています。 |
|
言語 |
ja |
| 書誌情報 |
en : Journal of the Physical Society of Japan
巻 84,
号 1,
p. 014002 -1-014002 -17,
発行日 2015-01
|
| 出版者 |
|
|
出版者 |
The Physical Society of Japan |
|
言語 |
en |
| ISSN |
|
|
収録物識別子タイプ |
PISSN |
|
収録物識別子 |
1347-4073 |
| 書誌レコードID |
|
|
|
識別子タイプ |
NCID |
|
|
関連識別子 |
AA00704814 |
| 論文ID（NAID） |
|
|
|
識別子タイプ |
NAID |
|
|
関連識別子 |
40020325424 |
| DOI |
|
|
関連タイプ |
isVersionOf |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.7566/JPSJ.84.014002 |
|
|
関連名称 |
10.7566/JPSJ.84.014002 |
| 著者版フラグ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |
AA00704814_v84n1_pp014002.pdf
