Shapes of Non-monotonous Activation Functions in Chaotic Neural Network Associative Memory Model and Its Evaluation
-
- Obayashi Masanao
- Graduate School of Sci. and Eng., Yamaguchi Univ.
-
- Omiya Rie
- Graduate School of Sci. and Eng., Yamaguchi Univ.
-
- Kuremoto Takashi
- Graduate School of Sci. and Eng., Yamaguchi Univ.
-
- Kobayashi Kunikazu
- Graduate School of Sci. and Eng., Yamaguchi Univ.
Bibliographic Information
- Other Title
-
- カオスニューラルネットワーク連想記憶モデルにおける活性化関数の形状とその評価
- カオスニューラル ネットワーク レンソウ キオク モデル ニ オケル カッセイカ カンスウ ノ ケイジョウ ト ソノ ヒョウカ
Search this article
Abstract
The purpose of this paper is to investigate the performance of the associative memory model using Aihara's chaotic neural network with different activation functions. Sigmoid function, a monotonous function, was used in Aihara's original model. However, in the static associative memory, it is reported that the storage capacity of the network is improved when a non-monotonous function is used as the activation function. To improve the associative ability of chaotic neural network, kinds of non-monotonous functions have been proposed to serve as activation function. This paper investigates their difference as to retrieval ability, and proposes an advanced non-monotonous function. By computer simulation, we discuss about what kind of shape is good to improve the associative ability of chaotic neural network.
Journal
-
- IEEJ Transactions on Electronics, Information and Systems
-
IEEJ Transactions on Electronics, Information and Systems 126 (11), 1401-1405, 2006
The Institute of Electrical Engineers of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204603985280
-
- NII Article ID
- 10018318461
-
- NII Book ID
- AN10065950
-
- ISSN
- 13488155
- 03854221
-
- NDL BIB ID
- 8560480
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed