libagf is a fast, innovative implementation of adaptive or variable-bandwidth kernel-based estimators for statistical classification, PDF estimation, and interpolation/non-linear regression. It is written in C++ and includes simple, command line executables as well as easy-to-use libraries.
Kandid is a system to evolve graphics. Graphics, in Kandid, are not drawn by hand. Instead, new forms can be found using genetic algorithms. To achieve this aim Kandid simulates evolution using sexual reproduction and mutation. But there is no fitness function inside the program. Only the user can decide what images are interesting. Populations and genes can be stored in XML format. Image calculation is based on Lisp-like expressions, Lindenmayer Systems, Iterated Function Systems, Linear Cellular Automata, Voroni diagrams, and layered textures or isosurfaces rendered by the Persistence of Vision raytracer.
dbacl is a digramic Bayesian text classifier. Given some text, it calculates the posterior probabilities that the input resembles one of any number of previously learned document collections. It can be used to sort incoming email into arbitrary categories such as spam, work, and play, or simply to distinguish an English text from a French text. It fully supports international character sets, and uses sophisticated statistical models based on the Maximum Entropy Principle.
Koalog Constraint Solver is a powerful constraint solver written in Java. It provides cutting-edge technology for solving satisfaction and optimization problems, including scheduling, time-tabling, resource-allocation, puzzles (sudoku.koalog.com is powered by Koalog Constraint Solver), and configuration (Koalog Configurator is powered by Koalog Constraint Solver).
The LTI-Lib is an object oriented library with algorithms and data structures frequently used in image processing and computer vision. It was developed at the RWTH-Aachen University as a part of many research projects on computer vision dealing with robotics, object recognition, sign language, and gesture recognition. It provides an object oriented C++ library that includes fast algorithms, which can be used in real applications.
Joone (Java Object Oriented Neural Engine) is an artificial neural network Java framework. It is used to build and train neural networks with a powerful visual environment. It has a modular design and can be easily extended by writing new modules to implement new learning algorithms or architectures.
GENESIS (short for GEneral NEural SImulation System) is a general purpose simulation platform that was developed to support the simulation of neural systems ranging from subcellular components and biochemical reactions to complex models of single neurons, simulations of large networks, and systems-level models. It was developed as a research tool to provide a standard and flexible means for constructing structurally realistic models of biological neural systems.
ffnet is a fast and easy-to-use feed-forward neural network training solution for Python. You can use it to train, test, save, load, and use an artificial neural network with sigmoid activation functions. Any network connectivity without cycles is allowed (not only layered). Training can be performed with several optimization schemes, including genetic alorithm based optimization. There is access to exact partial derivatives of network outputs versus its inputs. Normalization of data is handled automatically by ffnet.