跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/04 23:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:張俊偉
研究生(外文):Jyun-Wei Jhang
論文名稱:以粒子群最佳演算法訓練類神經網路
論文名稱(外文):Artificial Neural Networks Training by Particle Swarm Optimization
指導教授:蘇德仁蘇德仁引用關係
指導教授(外文):Te-Jen Su
學位類別:碩士
校院名稱:國立高雄應用科技大學
系所名稱:電子與資訊工程研究所碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2007
畢業學年度:95
語文別:英文
論文頁數:49
中文關鍵詞:類神經網路粒子群最佳演算法函數近似前饋網路
外文關鍵詞:Artificial neural networksParticle swarm optimizationFunction approximationFeedforward network
相關次數:
  • 被引用被引用:1
  • 點閱點閱:602
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本篇論文旨在使用粒子群體最佳演算法尋找類神經網路之最佳權重值。目前使用最多的類神經網路訓練法則為倒傳遞演算法,它是一個近似最陡坡降的演算法。最陡坡降法是一個最簡單但通常是最慢的最小化方法,優點是簡單且只要計算梯度,缺點是訓練時間通常比其它演算法長;由於受到初始權重值的影響,往往只能夠求得局部最佳解,而無法確保尋找到全域的最佳解。
粒子群最佳演算法的概念源自群體行為理論,啟發自觀察鳥群或魚群行動時,能透過個體間特別的訊息傳遞方式,使整個團體朝同一方向、目標而去,因此可避免陷入局部最佳解。最後本研究將獲得的結果與已經公開的其他方法經過分析,來驗證我們所提出來的方法可以獲得較佳的結果。
In this thesis, the optimal weights of the Artificial Neural Networks (ANN) are trained by Particle Swarm Optimization (PSO). One of the most commonly used training rules is the Back-Propagation (BP) method. It is well known that BP is an approximate steepest descent algorithm. The steepest descent algorithm is the simplest, and often the slowest, minimization method, the advantage of steepest decent algorithm is very simple, requiring calculation only of the gradient, the disadvantage of steepest descent algorithm is that training time is generally longer than other algorithms; based on initial weight values, it is often to find the local optimal solution but not global optimal solution.
PSO is inspired by the social behavior of animals, such as bird flocking or fish schooling, that social sharing of information among the individual of the populations, let the entire individuals move toward the target, hence the PSO can avoid getting into the local optimal solutions. Finally, the demonstrated examples are presented to illustrate the better performance of the proposed methodology (PSO-ANN).
Abstract in Chinese i
Abstract ii
Acknowledgement iv
Contents v
List of Figures vii
List of Tables viii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Overview of the Thesis 3
Chapter 2 Artificial Neural Networks 4
2.1 Introduction 4
2.2 Biological Inspiration 5
2.3 Neuron Model and Networks Topologies 7
2.3.1 Neuron Model 7
2.3.2 Networks Topologies 10
2.4 Learning Rules 12
Chapter 3 Particle Swarm Optimization 14
3.1 Swarm Intelligence 14
3.1.1 Ant Colony 14
3.1.2 Fish Schools and Bird Flocks 15
3.2 Evolutionary Computation 16
3.3 Particle Swam Optimization 18
Chapter 4 Neural Networks Training by PSO 24
4.1 Introduction 24
4.2 Back-Propagation Algorithm 25
4.2.1 Performance Index 26
4.2.2 Chain Rule 28
4.2.3 Sensitivities 30
4.2.4 Summary of Back-Propagation Algorithm 32
4.3 PSO Based on ANN Training 33
Chapter 5 Simulation Results 36
5.1 Introduction 36
5.2 Problem Definition 36
5.3 Simulation Results 37
Chapter 6 Conclusions 44
References 45
List of Publications 48
Biography 49
[1]. J. Kenndy and R. C. Eberhart, “Particle Swarm Optimization,” Proceedings of IEEE International Conference on Neural Networks, pp. 1942-1948, 1995.
[2]. R. C. Eberhart and J. Kennedy, “A New Optimizer Using Particle Swarm Theory,” Proceedings of the Sixth International Symposium on Micromachine and Human Science, Nagoya, Japan. pp. 39-43, 1995.
[3]. W. McCulloch and W. Pitts, “A Logical Calculus of the Ideas Immanent in Nervous Activity,” Bulletin of Mathematical Biophysics, vol. 5, pp. 115-133, 1943.
[4]. M. T. Hagan, H. B. Demuth, and M. Beale, Neural Network Design, Thomson Learning, 1996.
[5]. G. Kendall, “Neural Networks: Introduction to Artificial Intelligence,” http://www.cs.nott.ac.uk/~gxk/courses/g5aiai/006neuralnetworks/neural-networks.htm.
[6]. S. Haykin, Neural Networks: a Comprehensive Foundation, 2nd edition, Prentice Hall, 1999.
[7]. A. Zaknich, Neural Networks for Intelligent Signal Processing, World Scientific, 2003.
[8]. M. Dorigo and L. M. Gambardella, “Ant Colonies for the Traveling Salsman Problem,” BioSystems, vol. 43, pp. 73-81, 1997.
[9]. M. Dorigo and T. Stützle, Ant Colony Optimization, MIT Press, 2004.
[10]. E. Bonabeau, M. Dorigo, and G. Theraulaz, Swarm Intelligence: From Natural to Artificial Systems, Oxford University Press, 1999.
[11]. J. McQuaid, A Silent Invader Bursts into View, 1998, http://www.nola.com/speced/homewreckers/day1mainstory1.html.
[12]. F. Heppner and U. Grenander, “A Stochastic Nonlinear Model for Coordinated Bird Flocks,” The Ubiquity of Chaos, AAAS Publications, 1990.
[13]. Y. Shi and R. Eberhart, “A Modified Particle Optimizer,” Proceedings of the 1998 IEEE World Congress on Computational Intelligence, pp. 69-73, 1998.
[14]. Y. Shi and R. Eberhart, “Parameter Selection in Particle Swarm Optimization,” Proceedings of the 7th International Conference on Evolutionary Programming VII, Lecture Notes In Computer Science, vol. 1447, pp. 591-600, 1998.
[15]. F. Rosenblatt, “The Perceptron: a Probabilistic Model for Information Storage and Organization in the Brain,” Psychological Review, vol. 65, pp. 386-408, 1958.
[16]. K. Hornik, M. Stinchcombe, and H. White, “Multilayer Feedforward Networks are Universal Approximators,” Neural Networks, vol. 2, no.5, pp. 359-366, 1985.
[17]. J. B. Li and Y. K. Chung, “A Novel Back-propagation Neural Network Training Algorithm Designed by an Ant Colony Optimization,” IEEE/PES Transmission and Distribution Conference Exhibition: Asia and Pacific, pp. 1-5, 2005.
[18]. K. Adem and K. Dervis, “Training Recurrent Neural Networks for Dynamic System Identification using Parallel Tabu Search Algoruthm,” Proceedings of the IEEE International Symposium on Intelligent Control, pp. 113-118, 1997.
[19]. C. Blum and K. Socha, “Training Feed-forward Neural Networks with Ant Colony Optimization: an Application to Pattern Classification,” Fifth International Conference on Hybrid Intelligent Systems, pp. 233-238, 2005.
[20]. E. Alba and J. F. Chicano, “Training Neural Networks with GA Hybrid Algorithm,” Proceedings of GECCO, LNCS 3102, pp. 852-863, 2004.
[21]. K. Hornik, M. Stinchcombe, and H. White, “Univeral Approximation of an Unknown Mapping and its Derivatives using Multilayer Feedforward Networks,” Neural Networks, vol. 3, no.5, pp. 551-560, 1990.
[22]. D. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.
[23]. M. Gen and R. Cheng, Genetic Algorithms & Engineering Design, John Wiley & Sons, 1997.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top