Public Domain ANN/Fuzzy Systems Software Index

Multi-Layer Perceptron and ANN in general

• CASCOR -- Cascade Correlation BackProp Network (Cascor)
• QuickProp -- A quick and simple backProp learning algorithm (Quickprop)
• Matrix -- A matrix based backProp learning algorithm (mvp)
• PDP++ -- The PDP++ software is a neural-network simulation system written in C++. It represents the next generation of the PDP software originally released with the McClelland and Rumelhart "Explorations in Parallel Distributed Processing Handbook", MIT Press, 1987.
  As of August 21, 2007, PDP++ is replaced by emergent.
• MLC++ -- MLC++ is a library of C++ classes for supervised machine learning. The MLC++ utilities were created using the library. Official web site: http://www.sgi.com/tech/mlc/
• Win_nn: Implementation of fully connected multilayer perceptron in Window environment.
• Neural Network Utilities Programs -- This package is distributed in .zip file in a PC/Window environment. It contains some programs illustrating how to program a neural network in C. Please read the README file for more detail. Then you may want to down load the nnutl101.zip ZIP file.
• LNKnet pattern classification software. Official web site: http://www.ll.mit.edu/mission/communications/ist/lnknet/index.html
• Netlab neural network software: Window source code, and html help files. Official web site: http://www.ncrg.aston.ac.uk/netlab/

SOM, LVQ, and Clustering

• SOM_PAK -- Self Organizing Map (SOM) program source code, header files,
  For DOS/WINDOW platform, Down load this self-extracting file som_p3r1.exe.
  For Unix workstations, here is the som_pak-3.1.tar (tar file).
  Here is the README file and the documentation: som_doc.ps (Postscript); or som_doc.txt (Ascii).
  Official web site: http://www.cis.hut.fi/research/som-research/nnrc-programs.shtml
• SOM Tool Box -- Matlab-5 toolbox of SOM (Released by authors of SOM_pak. Current version 2.0 (March 2005)
  Official URL: http://www.cis.hut.fi/projects/somtoolbox/
  
• LVQ_PAK -- Learning Vector Quantization (lvq) program source code, header files,
  For DOS/WINDOW platform, Down load this self-extracting file lvq_p3r1.exe.
  For Unix workstations, here is the lvq_pak-3.1.tar (tar file).
  Here is README file and the documentation lvq_doc.ps (Postscript) or lvq_doc.txt (Ascii).
  Official web site: http://www.cis.hut.fi/research/som-research/nnrc-programs.shtml
• Neural Network System Identification Tool Box -- Directory of Neural Network System Identification toolbox released by Technical University of Denmark. Here is the README file.
• Clustering toolbox for Matlab. Official web site: http://www.tech.plym.ac.uk/spmc/links/classification/classification_matlab.html (require the installation of netlab)
• FastMix: Fast EM based Guassian Mixture Model generation. Official Web Site: http://www.cs.cmu.edu/~psand/

Support Vector Machine (SVM)

• Support Vector Machine Matlab Tool Box by S. Gunn. Contains PDF documents, and Zipped mfiles.
• SVM_Light A C implementation of SVM. The tar-gzipped file can be downloaded here. Current official web site: http://svmlight.joachims.org/
• LibSVM -- A SVM implementation for solving large scale difficult classification problems. LibSVM has many interfaces to different languages and operating systems. The latest version 2.8 has a very nice matlab interface in a zip file. Official web site of LibSVM is at: http://www.csie.ntu.edu.tw/~cjlin/

Miscellaneous

• Statistical pattern recognition toolbox. It is an implementation of selected methods described in the book: M.I. Schlesinger, V. Hlavac, Ten lectures on the statistical and structural pattern recognition, Kluwer Academic Publishers, 2002.
  Download the latest version at here, a local version can be found at here
• Genetic Algorithm Toolbox, released by the Evolutionary Computation Research Group of the university of Sheffield, UK.
• Modular toolkit for data processing -- MDP is a collection of supervised and unsupervised learning algorithms and other data processing units that can be combined into data processing sequences and more complex feed-forward network architectures.