Chaotic neural network is a neural network which consists of chaotic neurons. Chaotic neuron is an artificial neuron model that introduces chaos theory. Artificial neuron model is a computing system that imitates our brain. The purpose of this study is to observe the behavior of chaotic neural network and improve its learning ability with incremental learning.
Here, several experiments focusing on its parameter are conducted in order to achieve the goal. What is new compared with past researches treating the same theme is changing the value of the parameter while learning, whereas the others used a constant value for it. The parameter is delta weight(
), meaning how much it changes the weights' value. As a result, better performance can be shown.