Chaotic episodic associative memory

Article type: Research Article

Authors: Kitada, Junya^{; *} | Osana, Yuko | Hagiwara, Masafumi

Affiliations: Department of Information and Computer Science, Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kouhoku-Ku, Yokohama 223-8522, Japan. E-mail: [email protected]

Correspondence: [*] Correspoding author.

Abstract: In this paper, we propose a chaotic episodic associative memory (CEAM). It can deal with complex episodes which have common terms. The proposed CEAM is based on the conventional temporal associative memory and has connections in the input layer for autoassociation. Each scene of the episodes is memorized together with its own contextual information. The CEAM employs chaotic neurons in a part of the input layer corresponding to contextual information. The chaotic neurons change their states by chaos. As a result, the CEAM can associate plural episodes that have common terms.

DOI: 10.3233/ICA-2000-7305

Journal: Integrated Computer-Aided Engineering, vol. 7, no. 3, pp. 243-251, 2000