论文信息 - Simulation and Research for Forward Neural Networks Modeling

Simulation and Research for Forward Neural Networks Modeling

This paper presents analysis and experiments for Forward Neural Networks (FNN) modeling based on software simulation. First, we illustrate this modeling method in detail. Then the algorithm flow charts of four learning algorithms, including Back Propagation (BP), Modified BP (MBP), Davidon Least Square based algorithm and Damping Least Square based algorithm are given. In addition, a simulation software for training and testing FNN is developed using these algorithms. In the last, we compare and analyze the performance of these four algorithms based on simulation experimental results.

Li Qiang | Zhang Yanxue

[1] Peter J. Gawthrop,et al. Neural networks for control systems - A survey , 1992, Autom..

[2] Richard D. Braatz,et al. On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[3] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.

[4] Philipp Slusallek,et al. Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[5] William M. Conner. The Dimension of a Formal Language , 1975, Inf. Control..

[6] E.D. Di Claudio,et al. LS-based training algorithm for neural networks , 1993, Neural Networks for Signal Processing III - Proceedings of the 1993 IEEE-SP Workshop.

[7] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[8] G. Kane. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .