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.
OpenEphyra is a question answering (QA) system. It retrieves answers to natural language questions from the Web and other sources. OpenEphyra comes with implementations of algorithms that proved effective in Carnegie Mellon's Ephyra system, which participated in the TREC evaluations. It is platform independent and can be set up in just a few minutes. The goal of this project is to give researchers the opportunity to develop new QA techniques without worrying about the end-to-end system.
ASpiReNN is a little C library (with Python bindings) which provides support for simple (leaky integrate-and-fire) spiking neural networks. It is primarily designed for highly recurrent networks, but it can also be used with multi-layer nets, though performance won't be the same. Though only Leaky integrate-and-fire (for the neurons) and Spike-Timing Dependent Plasticity (for learning rules) are currently implemented, adding new models shouldn't be too difficult.
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.
Fast Artificial Neural Network Library is a neural network library that implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast. C++, Perl, PHP, .NET, Python, Delphi, Octave, Pure Data, and Mathematica bindings are available. A reference manual accompanies the library with examples and recommendations on how to use the library. A graphical user interface is also available for the library.
Player provides a language-independent networked interface to robots and their sensors. Supported devices include Pioneer 2DX robots with sonar, odometry & compass, SICK laser rangefinder, ACTS color vision system, GPS, gripper and wireless communications. Stage provides a population of simulated Player devices. Controllers designed using Stage have been shown to work unchanged on real robots and vice versa. Stage aims for low-fidelity simulation of many devices, rather than perfect models.
Proper nouns is a PHP class that can extract proper nouns from texts. It takes a text string and can detect which words may be proper nouns of people or other entities. It uses some heuristics like the capitalization of the first letter of a word, the presence of a person's title preceding the nouns, etc. The class may consider consecutive proper names as a single proper name. The class assumes English by default but may be configured to work with other idioms.
EO is a template-based, ANSI-C++ evolutionary computation library that helps you to write your own stochastic optimization algorithms quickly. Evolutionary algorithms form a family of algorithms inspired by the theory of evolution, and solve various problems. They evolve a set of solutions to a given problem in order to produce the best results. These are stochastic algorithms because they iteratively use random processes. The vast majority of these methods are used to solve optimization problems, and may be also called "metaheuristics". They are also ranked among computational intelligence methods, a domain close to artificial intelligence. With the help of EO, you can easily design evolutionary algorithms that will find solutions to virtually all kind of hard optimization problems, from continuous to combinatorial ones.
Augmented Syntax Diagrams (ASDs) provide a way to represent grammars of natural languages as directed graphs. Nodes represent instances (or usages) of words and phrase types in a language such as English. Edges link nodes together to indicate how instances of words and phrase types can follow one another to make up phrases, clauses, and sentences in the language.