JaNet: Java neural Network Toolkit
resume: A well documented toolkit for designing and training, and a java library for inclusion in third party programs.
description: jaNet package is a java neural network toolkit, which you can use to design, test, train and optimize an ideal neural Network for your private application. You can then include your saved network in your program using the jaNet.backprop package. The consequent documentation is only in french for the moment, but an english translation is planned. The java source code is released under GPL, and can be compiled with JDK, Symantec Cafe or MS Visual J
This demo nstrates the use of the reversible jump MCMC algorithm for neural networks. It uses a hierarchical full Bayesian model for neural networks. This model treats the model dimension (number of neurons), model parameters, regularisation parameters and noise parameters as random variables that need to be estimated. The derivations and proof of geometric convergence are presented, in detail, in: Christophe Andrieu, Nando de Freitas and Arnaud Doucet. Robust Full Bayesian Learning for neural Networks. Technical report CUED/F-INFENG/TR 343, Cambridge University Department of Engineering, May 1999. After downloading the file, type "tar -xf rjMCMC.tar" to uncompress it. This creates the directory rjMCMC containing the required m files. Go to this directory, load matlab5 and type "rjdemo1". In the header of the demo file, one can select to monitor the simulation progress (with par.doPlot=1) and modify the simulation parameters.
這程序是《神經(jīng)網(wǎng)絡(luò)模式識別及其實(shí)現(xiàn)》（Pattern Recognition with neural Networks in C++)美Abhijit S. Pandya等著電子工業(yè)出版社1999年6月
書號ISBN 7-5053-5088-9
