臺灣博碩士論文加值系統

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.

誌謝 ...............................................................................................................................i
中文摘要 ......................................................................................................................ii
英文摘要 .....................................................................................................................iii
目錄 .............................................................................................................................iv
圖目錄 ..........................................................................................................................v
表目錄 ........................................................................................................................vii

第一章 緒論 ..............................................................................................................1

1.1 研究動機與目的 ..........................................................................................1
1.2 研究架構 ......................................................................................................1

第二章 修正式粒子群聚最佳化演算法 ..................................................................3

2.1 粒子群聚最佳化演算法 ..............................................................................3
2.2 Lévy Flight ....................................................................................................6
2.3 加強式粒子群聚最佳化演算法 ..................................................................8
2.4 修正式粒子群聚最佳化演算法 ..................................................................9

第三章 類神經網路 ................................................................................................14

3.1 類神經網路之架構 ....................................................................................14
3.2 使用粒子群聚最佳化演算法於類神經網路之訓練 ................................19

第四章 例題示範 ....................................................................................................21

第五章 結論與討論 ................................................................................................36

參考文獻 ....................................................................................................................37

[1]https://www.cs.ccu.edu.tw/~ckting/ec.html
[2]https://zh.wikipedia.org/wiki/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4
%B9%A0
[3]X.S. Yang and S. Deb., "Cuckoo search via Levy flights," in Proceedings of World Congress on Nature & Biologically Inspired Computing, India, IEEE publications, pp. 210-214, 2009.
[4]X.S. Yang and S. Deb., "Engineering optimization by cuckoo search," International Journal of Mathematical Modeling and Numerical Optimization, vol. 1, no. 4, pp. 330-343, 2010.
[5]H. Soneji and R. C. Sanghvi, "Towards the improvement of Cuckoo search algorithm, " IEEE World Congress on Information and Communication Technologies, pp. 878-883, 2012.
[6]P. Gries, J. Campbell, and J. Montojo, Practical Programming: An Introduction to Computer Science Using Python 3, 2nd ed. Dallas: Pragmatic Bookshelf, 2013.
[7]J.V. Guttag, Introduction to Computation and Programming Using Python, London: MIT Press, 2013.
[8]M. Lutz, Python Pocket Reference, 5nd ed. Santa Clara: O''Reilly Media, 2014.
[9]郭英勝、鄭志宏、龔志銘、謝哲光，實用Python程式設計，松崗，台北，台灣，2016。
[10]R.C. Eberhart and J. Kennedy, "A new optimizer using particle swarm theory," in Proceeding of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan, pp. 39-43, 1995.
[11]J. Kennedy and R.C. Eberhart, "Particle swarm optimization," in Proceeding of IEEE International Conference on Neural Networks, Perth, Australia, vol. 4, pp. 1942-1948, 1995.
[12] J. Kennedy and R.C. Eberhart, Swarm Intelligence, Morgan Kaufmann, San Francisco, California, USA, 2001.
[13] https://en.wikipedia.org/wiki/Paul_L%C3%A9vy_(mathematician)
[14]https://en.wikipedia.org/wiki/Random_walk
[15]https://en.wikipedia.org/wiki/L%C3%A9vy_flight
[16]https://en.wikipedia.org/wiki/Differential_evolution
[17]R. Jensi and G.W. Jiji, "An enhanced particle swarm optimization with levy flight for global optimization," Applied Soft Computing. vol. 43, pp. 248-261, 2016.
[18]H. Haklı and H. Uguz, "A novel particle swarm optimization algorithm with Levy flight," Applied Soft Computing. vol. 23, pp.333-345, 2014.
[19] S.H. Pakzad-Moghaddam, "A Lévy flight embedded particle swarm optimization for multi-objective parallel-machine scheduling with learning and adapting considerations," Computers & Industrial Engineering. vol. 91, pp. 109-128, 2016.
[20]N.D. Jana and J. Sil, "Particle swarm optimization with Lévy flight and adaptive polynomial mutation in gbest particle," In: Thampi S., Abraham A., Pal S., Rodriguez J. (eds), Recent Advances in Intelligent Informatics. Advances in Intelligent Systems and Computing, vol. 235, Springer, Cham, Germany, 2014, pp. 275-282.
[21]https://zh.wikipedia.org/wiki/%E4%BA%BA%E5%B7%A5%E7%A5%9E%
E7%BB%8F%E7%BD%91%E7%BB%9C
[22]https://zh.wikipedia.org/wiki/%E6%84%9F%E7%9F%A5%E5%99%A8
[23] J.G. Hsieh, Pathways to Machine Learning and Soft Computing, Lecture Notes, Department of Electrical Engineering, I-Shou University, Kaohsiung, Taiwan, 2017 (unpublished).
[24]I.C. Trelea, "The particle swarm optimization algorithm: Convergence analysis and parameter selection," Information Processing Letters, vol. 85, pp. 317-325, March 2003.