论文信息 - Training Neural Networks With Influence Diagrams

Training Neural Networks With Influence Diagrams

This paper discusses the application of Influence Diagrams on training Neural Networks. The basic concepts of these two methodologies are presented as a brief review. The conventional back-propagation training procedure is compared to other alternatives, by means of an example on visual pattern recognition.

Mario Fernando Montenegro Campos | Alexei Manso Corrêa Machado

[1] Eric Horvitz,et al. Decision Analysis and Expert Systems , 1991, AI Mag..

[2] D. Bertsekas,et al. Introduction to Probability , 2002 .

[3] Judea Pearl,et al. Distributed Revision of Composite Beliefs , 1987, Artif. Intell..

[4] Judea Pearl,et al. Fusion, Propagation, and Structuring in Belief Networks , 1986, Artif. Intell..

[5] James L. McClelland,et al. James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[6] David J. Spiegelhalter,et al. Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[7] Julius T. Tou,et al. Pattern Recognition Principles , 1974 .

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

[9] R. Palmer,et al. Introduction to the theory of neural computation , 1994, The advanced book program.