Genetic Algorithms for MLP Neural Network Parameters Optimization

摘要：

In this paper, a hybrid learning algorithm for a Multilayer Perceptrons (MLP) Neural Network using Genetic Algorithms (GA) is proposed. This hybrid learning algorithm has two steps: First, all the parameters (weights and biases) of the initial neural network are encoded to form a long chromosome and tuned by the GA. Second, as a result of the GA process, a quasi-Newton method called Broyden-Fletcher-Goldfarb-Shannon (BFGS) method is applied to train the neural network. Simulation studies on function approximation and nonlinear dynamic system identification are presented to illustrate the performance of the proposed learning algorithm.

关键词： Genetic Algorithms Backpropagation Function Approzimation Nonlinear Dynamic System Identification

作者: Meng Joo Er Fan Liu

作者单位: School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 3653-3658

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）