Improved Chaotic Associative Memory for Successive Learning

Authors:
Takahiro Ikeya;Takehito Sazuka;Akira Hagiwara;Yuko Osana
Affiliations:
Tokyo University of Technology, Hachioji, Tokyo, Japan;Tokyo University of Technology, Hachioji, Tokyo, Japan;Tokyo University of Technology, Hachioji, Tokyo, Japan;Tokyo University of Technology, Hachioji, Tokyo, Japan
Venue:
AIA '08 Proceedings of the 26th IASTED International Conference on Artificial Intelligence and Applications
Year:
2008

Citing 4
Cited 1

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Pattern Recognition by Self-Organizing Neural Networks

Pattern Recognition by Self-Organizing Neural Networks
Hetero chaotic associative memory for successive learning with give up function: one-to-many associations

AIA'06 Proceedings of the 24th IASTED international conference on Artificial intelligence and applications

Improved Kohonen Feature Map Associative Memory with Area Representation for Sequential Analog Patterns

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose an Improved Chaotic Associative Memory for Successive Learning (ICAMSL). The proposed model is based on a Hetero Chaotic Associative Memory for Successive Learning with give up function (HCAMSL) and a Hetero Chaotic Associative Memory for Successive Learning with Multi-Winners competition (HCAMSL-MW) which were proposed in order to improve the storage capacity. In most of the conventional neural network models, the learning process and the recall process are divided, and therefore they need all information to learn in advance. However, in the real world, it is very difficult to get all information to learn in advance. So we need the model whose learning and recall processes are not divided. As such model, although some models have been proposed, their storage capacity is small. In the proposed ICAMSL, the learning process and the recall process are not divided. When an unstored pattern is given to the network, it can learn the pattern successively, and its storage capacity is larger than that of the conventional HCAMSL/HCAMSL-MW.