本研究是以修正式粒子群聚最佳化演算法 (modified Particle Swarm Optimization) 訓練類神經網路進行機器學習。此修正式演算法將標準的粒子群聚最佳化演算法 (Particle Swarm Optimization, PSO) 與 Lévy Flight (常用於布穀鳥演算法, Cuckoo Search algorithm) 做適度的結合,透過修正粒子群聚最佳化演算法中的更新公式,使粒子在搜尋最佳解時不易陷入區域最佳解 (local minima) 而無法跳脫的缺陷,並且避免候選解有過早收斂 (premature convergence) 的問題。我們將以三個例題示範如何使用本研究所提出的演算法,並將比較所提出的演算法與標準的粒子群聚最佳化演算法之表現。本研究使用 Python 程式語言撰寫程式。
In this research, the modified particle swarm optimization algorithm will be applied to the training of artificial neural networks for machine learning problems. This modified algorithm appropriately combines the standard particle swarm optimization and Lévy flight (very often used in cuckoo search algorithm) in order to escape from the local minima of the cost surface and to avoid the premature convergence of the candidate solutions. Three numerical examples will be used to illustrate the use of our proposed algorithm. Some comparisons of the performances using proposed algorithm and the standard particle swarm optimization will be made. Our programs were written in Python language.