OpenAI is a project which is centred around the advancement of Artificial Intelligence. The project itself is geared toward developing specifications for AI and a default implementation for a set of well known AI tools. This is OpenAI's Neural Network release. The software is written in Java and is built in a modular fashion so that new algorithms and learning rules can be created. Configuration and persistence will be done through XML and a CORBA interface is provided for applications that wish to incorporate the technology.
The OpenAI project is centered around the advancement of Artificial Intelligence. It is geared toward developing specifications for AI and a default implementation for a set of well-known AI tools. The genetic algorithm is written in Java and is built in a modular fashion so that new algorithms and evolution rules can be created.
AI::GA implements a (hopefully) generalized genetic algorithm. It does this by using an array of allowed tokens as individuals. The user has to provide a fitness function. There, the actual representation is implemented. If you have a string of chars, you can simply join them. If you want to have real numbers, you should probably use a bitwise representation and calculate the real values in your fitness function.
PyStem is a fast Python module with the the Porter stemming algorithm (a process for removing the commoner morphological and inflexional endings from words in English; its main use is as part of a term normalisation process that is usually done when setting up Information Retrieval systems).
Torch is a machine learning library written in C++ that works on most Unix/Linux platforms. It can be used to train MLPs, RBFs, HMMs, Gaussian Mixtures, Kmeans, Mixtures of experts, Parzen Windows, KNN, and can be easily extended so that you can add your own machine learning algorithms.
The RoboCup Soccer Simulator is a platform for evaluating multiple autonomous intelligent agents in a realworld-like domain. The simulator allows two teams of 11 players and one coach to interact in a simulated game of soccer. The team members connect to the simulator using UDP sockets and must perform complex behaviors using only a few basic commands, primarily dash, kick, turn, and catch, based on noisy and infrequent sensor information provided by the simulator. This simulator is used in the simulation league of the RoboCup competition.
The Freehand Formula Entry System is a research prototype for recognizing online handwritten mathematical notation, developed jointly by researchers in New Zealand, the United States and Canada. A user draws expressions with a mouse or data tablet, and LaTeX, a bitmap, and an operator tree are produced as output. Symbol recognition and expression interpretation are performed as the user draws.