Today, ``neural networks'' play an important 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 actions 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 earlier studis, only single pattern was learned by the chaotic neural networks. And last year, our group suceeded in making the chaotic neural networks learn two cyclic patterns by associative memory.
But it was only cheked that two cyclic patterns ware recalled in last year. So in this paper, it was controled parameter of chaotic neuron by presynaptic inhibition and agree rate with a landmark pattern and recalled cyclic pattern that contain a landmark pattern. As a result cyclic pattern was successfully recalled by me.