Properties of a chaotic network separating memory patterns
Paweł Matykiewicz · 2005
A simple method aimed at improving the separation abilities of a chaotic neural network is presented and its memory properties investigated. Estimation of the invulnerability to the external input disturbance and the damage of weight connections are performed. Significant improvements of retrieval characteristic are reported. When weight connections are damaged, high instability of separation of the memory patterns is observed.