Separation of superimposed pattern and many-to-many associations by chaotic neural networks

In this paper, we propose a Chaotic Associative Memory (CAM). It has two distinctive features: (1) it can recall correct stored patterns from superimposed input; (2) it can deal with many-to-many associations. As for the first feature, when a stored pattern is given to the conventional chaotic neural network as an external input continuously, around the input pattern is searched. The proposed model makes use of the above property in order to separate superimposed patterns. As for the second one, most of the conventional associative memories can not deal with many-to-many associations because the superimposed pattern caused by the stored common data. However, since the proposed model can separate the superimposed pattern, it can deal with many-to-many associations. A series of computer simulations shows the effectiveness of the proposed model.