Today, ``neural networks'' play an important role in the field of image processing and pattern perception. They enable computers to simulate the actions by the model of human nerve cells.
Further, neural networks developed into chaotic neural networks adopting the ``chaos'' in order to near actual human nerve cells. Chaotic neural networks that learned patterns by auto-correlative associative memory can recall the acyclic patterns including learned patterns.
In this study, chaotic neural networks search for cyclic associative memories. The learned patterns by networks are 30 portrait's patterns, and 30 portrait's patterns are used for cyclic memories of 5 kinds of 6 cycles.