Hetero Chaotic Associative Memory for Successive Learning with Give Up Function –One-to-Many Associations–

T. Arai and Y. Osana (Japan)

Keywords

Associative Memory, Chaotic Neural Network, Successive Learning, Give Up Function, OnetoMany Associations

Abstract

In this paper, we propose a Hetero Chaotic Associative Memory for Successive Learning (HCAMSL) with give up function. The proposed model is based on a Chaotic As sociative Memory for Successive Learning (CAMSL). In most of the conventional neural network models, the learn ing process and the recall process are divided, and there fore 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, al though some models have been proposed, most of them can deal with only auto-associations. In contract, the proposed HCAMSL can deal with hetero-associations. In the pro posed HCAMSL, the learning process and the recall pro cess are not divided. When an unstored pattern is given to the network, the HCAMSL can learn the pattern succes sively. We carried out a series of computer experiments and confirmed the effectiveness of the proposed HCAMSL.

Important Links:



Go Back