Today, ``neural networks'' play an inportant role in the field of image processing and pattern perception.
The ``neuron model'' which is used in neural networks is the model of nerve cells, and it enables computers to simulate the action of the nerve cells. The usual neuron model treats only their basic actions. Therefore, by introducing the chaos that is detected from nerve cells to the usual neuron, chaotic neuron becomes nearer and nearer to the nerve cells.
In this study, I realize search access by chaotic neural networks.
The networks learns four patterns by associative memory and learns features of patterns by back propagation.
The search access does not search target pattern by inputing a pattern, but it searches target pattern inputing a feature of a pattern.
And, I realize the networks that can search target pattern with any parameter and any feature.