結合基因法則之類神經網路技術-演化型類神經網路

Abstract

本論文主要在研究實數編碼排序式基因法則，其染色體使用浮點數形式參數，此方法的排列式適應函數可以增加族群的變異性，此外在演化過程中，採用排序式重生及實數型交配、突變來產生子代。本論文還提出一種結合實數編碼排列式基因法則和倒傳遞演算法的新方法-演化型類神經網路，此類神經網路將人類的特性學習行為融合到演化當中。它不僅可改善倒傳遞演算法容易掉入區域最小解的缺點而且能夠克服基因法則無法有效收斂至鄰近區域最小解的困難。最後，將實數編碼排列式基因法則應用在尋找狀態回授控制器參數的問題上以展現它搜尋能力，也將演化型類神經網路應用在有名的或斥問題上來顯示它的優點。

This thesis presents a Real-Coded Rank-Based Genetic Algorithm (RCRBGA), which is represented by a chromosome containing parameters in floating-point. The use of rank-based fitness increases the population diversity. The offspring are generated by the rank-based reproduction, real parametric crossover and mutation in the evolving process. Besides, an Evolutionary Neural Network (ENN) which combines RCRBGA and Back-Propagation (BP) is introduced. ENN applies the learning concept to the evolution process, like the behavior of human beings. It not only improves the disadvantage of easily slumping in to local minima of BP but also overcomes the defect of genetic algorithm, which can't efficiently converge to minima. Finally, the search ability of RCRBGA is demonstrated by an example, linear state-feedback controller via pole-assignment method. In addition, ENN applies to a classifying problem of the modified XOR to show its advantage.