Search Results for "gnu science" - Page 14

Dinapter automatically generates a mapping between methods of incompatible components/services based on their public interfaces and behaviors. It uses a combination of expert system and A* algorithm. Dinapter is the prototype resulting from a couple of research papers: * J.A. Martín, E. Pimentel. Automatic Generation of Adaptation Contracts, FOCLASA'08, ENTCS, 2008 - http://goo.gl/21iJZ * J.A. martín, E. Pimentel. Dinapter: Automatic Adapter Specification for Software Composition,...

This project provides a set of Python tools for creating various kinds of neural networks, which can also be powered by genetic algorithms using grammatical evolution. MLP, backpropagation, recurrent, sparse, and skip-layer networks are supported.

The Moses repository has moved: https://github.com/moses-smt/mosesdecoder Factored phrase-based, hierarchical and syntax decoder for statistical machine translation

DHAC distribution

The Deep Email Miner Application is a software solution for the multistaged analysis of an Email Corpus. Social network analysis and text mining techniques are connected to enable an in depth view into the underlying information. The self-executable Version 1.1 jar file will now run on Java 1.5 or higher. A Windows executable file of Version 1.1 is also provided in the Files section. Documentation can be found on the project homepage.

Bamboo intends to be a complete end-to-end game framework for client/server applications using Twisted for data exchange, Panda3D for rendering and coded in Python. Support for PyPy/CPython may be considered at a later point. An Extreme/Agile Development model is in use to allow for emergent design (IE: changing requirements). Release is updated whenever a feature is added and all tests pass cleanly 100%

This project implements the techniques used in this paper: @INPROCEEDINGS{Andres10a, author = {Jesús Andrés-Ferrer and Germán Sanchis-Trilles and Francisco Casacuberta}, title = {Similarity Word-Sequence Kernels for Sentence Clustering}, booktitle = {Proceedings of the 8th International Workshop on Statistical Pattern Recognition}, year = {2010}, } This project depends on jaf_Utils: http://sourceforge.net/projects/jafutils/ Install it prior...

NaruGo is game AI project. Current targets are GO board game and Texas Holdem poker. It investigates Genetic programming to build game AI logic. Also EA/GP simulations for TSP, Graph layout and Prisoners Dilemma problem.

This Java software implements Profile Hidden Markov Models (PHMMs) for protein classification for the WEKA workbench. Standard PHMMs and newly introduced binary PHMMs are used. In addition the software allows propositionalisation of PHMMs.

It's an object-oriented library written in C++ for creating arbitrary kind of neural networks. The user can use the classes provided to create neural network with arbitrary topology and mixed type of neurons. It's very easy add custom neurons.

GPalta is a genetic programming toolbox that aims for simplicity and speed. It features tree-based genetic programming, optional strong typing, a GUI to control an evolution process (allows to save and continue later) and easy interoperability with Matlab

This is an effort to create the best yet simple sudoku solver.

Flipper is a program that does randomised local search for satisfiability of 3 variable prenex sentences in the pure predicate calculus. It does so by proving satisfiability relative to given decidable theories.

3-layer neural network for regression and classification with sigmoid activation function and command line interface similar to LibSVM. Quick Start: "java -jar nen.jar"

UNIMATRIX is a students project from the "University of Applied Sciences Fulda" managed by Prof. Dr. Oleg Taraszow. We design an autonomous team of robots playing soccer in the RoboCup Small-Sized League.

The PYthon LInguistic Laboratory (pylilac) is a Python library and a set of tools to help in studying, analyzing and engineering languages.

TestEl is a Java-based learning analyzer for HTML (and possibly other) structured documents. It can be trained to detect structures in such documents and renders hits in XML.

The main intention of this project is to support the SNNS (Stuttgart Neural Net Simulator) with patches, bugfixes, tools and add on developments. Second target is to publish useful links and information about the SNNS.

An omnifont OCR engine. The long-term goal is recognition of formulas.

Arena is a computer simulation in which programs compete for CPU time and access to main memory. Processes such as the dynamics of punctuated equilibrium, host-parasite co-evolution and density dependent natural selection are amenable to investigation.

ADIC (any door is closed) is a cooperative multiplayer game. The goal is to lock all players of the other team. Beside of playing the game you can write a bot and use the game as testbed for AI/robotics algorithms.

A modular implementation of various algorithms and techniques of Machine Vision, and a 3D virtual environment for demonstration, a project for UCM (Universidad Complutense de Madrid).

This project aims to build a suite of Natural Language Processing tools. Modules will include corpus indexing and access tools, a part-of-speech tagger, tokenisers, text classification software, etc.

Open Metaheuristic (oMetah) is a library aimed at the conception and the rigourous testing of metaheuristics (i.e. genetic algorithms, simulated annealing, ...). The code design is separated in components : algorithms, problems and a test report generator

Vedvarsha is an application for 2 purposes: 1. Handwariting script recognition that extracts recognized letters into documents. 2. OCR (Optical Character Recogniton) that works only for non-cursive and isolated characters. It depends upon libsyntactic,