论文信息 - Learning by diffusion for multilayer perceptron

Learning by diffusion for multilayer perceptron

A method of nonlinear optimisation based on simulating diffusion processes is discussed and applied as a self-organisation or learning tool for the multilayer perceptron neutral network. Results indicate significant improvements over conventional learning methods. The new method can be easily implemented in existing hardware. >

Trevor J. Hall | R. G. Hoptroff

[1] D. E. Rumelhart,et al. Learning internal representations by back-propagating errors , 1986 .

[2] Donald Geman,et al. Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.