Projects with the tag “neural”

BPNN++ is an implementation of a feed-forward back-propagation neural network, with a maximum of 2 hidden layers, in C++. It comes as a simple C++ header file with no external dependencies. It uses C++ templates to be both fast and memory efficient.

The goal of this project is to create NN which elements are complex numbers (a+ib)

The FAKE GAME tool uses natural evolution to evolve Data Mining models. It incorporates several preprocessing, optimization and visualization methods aimed to streamline the Knowledge Discovery process. Knowledge Extraction from data is being automated!

ffnet is a fast and easy-to-use feed-forward neural network training solution for python. Many nice features are implemented: arbitrary network connectivity, automatic data normalization, very efficient training tools, network export to fortran code.

jHRT - java Handwriting Recognition Tool is developed to recognize hand written letter and characters. It's engine derived's from the Java Neural Network Framework - Neuroph and as such it can be used as a standalone project or a Neuroph plug in.

GAME stays for Generic Architecture based on Multiple Experts. Its main purpose is to make easy prototyping, test and release of prediction systems. Released by IASC group, university of Cagliari

This project is aimed at making a complete flexible Neural network library in java. The library works fine with most complex problems.The current implementation needs modification to allow user to change Learning rate and Momentum.

The Java Data Mining Package (JDMP) is a library that provides methods for analyzing data with the help of machine learning algorithms (e.g. clustering, classification, graphical models, neural networks, Bayesian networks, text processing, optimization).

Kohonen neural network library is a set of classes and functions for design, train and use Kohonen network (self organizing map) which is one of AI algorithms and useful tool for data mining and discovery knowledge in data (http://knnl.sf.net).

An open source face recognition project.

Multiple Back-Propagation is an open source software application for training neural networks with the backpropagation and the multiple back propagation algorithms. Currently this project is also hosted at http://code.google.com/p/multiplebackpropagation

Example of using Neural networks to implement chase between mouses and cats. Mouses search for cheese on map, while cats are chasing mouses. Goal of the project is to see will both sides learn some new behavior over time using genetic algorithms.

Neuroph is lightweight Java Neural Network Framework which can be used to develop common neural network architectures. Small number of basic classes which correspond to basic NN concepts, and GUI editor makes it easy to learn and use.

NNF2 is a C++ library for feed-forward neural networks (also called multi-layer perceptrons). Its modular design makes it easily extensible by users. Batch training and saving of networks are supported.