Design of Chaotic Neural Network for Robust Phoneme Recognition

Recent developments in nonlinear dynamics and the theory of chaos have shown the existence of deterministic chaotic property in processing behavior of biological processing systems and human voice production. According to the natural selection theory a good problem-solver should have two main properties: The ability of emerging various solutions for problem and existence of a rule (or intelligence) to guide this evolution and variety to become close to the goal. We used chaotic nodes with logistic map to make the ability of emerging various solutions. We designed a rule using RBNN In order to control the evolution of chaotic nodes intelligently. The performance of proposed chaotic neural network is 66% whereas the performance of RBNN is 25% in the same noisy condition.