Evolutionary Particle Swarm Optimization for Neural Networks Learning Using Emotional Cue

摘要：

To deal with the flaws of BP learning algorithm during neural networks training, a novel learning algorithm for artificial neural networks (ANN) is proposed based on particle swarm optimization (PSO) in this paper. The method firstly introduces information entropy into PSO to quicken the convergence process of the particles. On the basis of it, emotional signal similar to human then is applied to each particle, thus each particle adjusts own state in light of its emotional signal, the convergence speed of the particle therefore is further improved, moreover, collective stability is also enhanced, dramatically. In the end, a simulation example in Short-Term Load Forecasting (STLF) for power systems indicates the validity of the proposed method.

作者: Hongsheng Su Youpeng Zhang

作者单位: School of Automatic and Electrical Engineering Lanzhou Jiaotong University Lanzhou ,730070, P.R.China

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）