Neural networks have recently begun to be utilized in many fields. Originally, the system was used for logical operation, and later for recognition of pattern and character, voice and so on. It is also applied for the estimate of weather and stock prices or control of machinery.
The neural network is one which imitated the nervous system in the brain, and a chaotic neuron is modeled after the nerve cell.
In this study, the back-propagation learning method is applied to chaotic parameters in a chaotic neuron. A 3-layer perseptron using chaotic neurons learn a series temperature with the back-propagation learning method and predict the temperature of next day.
Two kinds of network predict the temperature in learned and in not learned term. And, a network in normal neuron are compared with one in chaotic neuron.