Hetero chaotic associative memory for successive learning with give up function: one-to-many associations
Toshihiro Arai, Yuko Osana · International conference on Artificial intelligence and applications · 2006
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 Associative Memory for Successive Learning (CAMSL). In most of the conventional neural network models, the learning process and the recall process are divided, and therefore 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, most of them can deal with only auto-associations. In contract, the proposed HCAMSL can deal with hetero-associations. In the proposed HCAMSL, the learning process and the recall process are not divided. When an unstored pattern is given to the network, the HCAMSL can learn the pattern successively. We carried out a series of computer experiments and confirmed the effectiveness of the proposed HCAMSL.