Search Results for "gnu linux" - Page 76

Multilayered feed-forward neural network software written in C++. Backpropagation and RPROP are available as training algorithms. Design goals: speed of execution when calculating the output to new data, and quality of training (preprocessing: PCA).

DIET Agents is a lightweight, scalable and robust multi-agent platform in Java. It is especially suitable for rapidly developing P2P prototype applications and/or adaptive, distributed applications that use bottom-up, nature-inspired techniques.

Do you want a neural network OO class? With documentation? Do not go further... You found it! you have here a complete library of different neural network in an OO encapsulation. Starting from adaline, back propagation, Kohonen

JPop is a plugin that integrates the poplog (http://sourceforge.net/projects/openpoplog) environment as a plugin for the jedit (http://sourceforge.net/projects/jedit) programmers editor. The plugin is written in a mixture of Java, pop11, and beanshel

A neural net module written in python. The aim of the project is to provide a large set of neural network types accessed by an API that is easy to use and powerful.

mbFuzzIT enables the work with Fuzzy technology (fuzzy inference / fuzzy logic) in Java. In order to facilitate the creation of the inference mechanisms, mbFuzzIT containts a visual editor.

DTW is intended to be a Voice in -> Pictures + Text out program written in java using Sphinx from CMU. This is intended to be useful to people who have good oral/visual literacy skills but poor written literacy skills.

M-ICE is a modular hostbased intrusion detection framework. It is used as middleware to close the gap between IDS research and IDS development. M-ICE consists of various parts that can be connected together by using network-or interprocess-communication

SimpleDomino is a Server for a Programming Competition from Schoolinux and Linux-dubai.com for School Students. It uses TCP/IP for Communications. (It's base on Linux but can port to Windows) You can start your own Competition or Help us to develop this P

Evomusic deals with automatic composition of music (midi-files) using evolutionary algorithms. Currently we are testing multiple approaches for doing this successfully, especially neural networks and/or algorithms based on simple music theory.

myMAS is a framework for writing distributed, agent based Java applications.

This library implements self-organizing neural networks, also called Kohonen Nets. They can be used for high dimensional data analysis. Example: content based image recognition ( CBIR ).

Projects by the University of Missouri, Rolla Robotics Team. Includes: software for raceing off road autonomously(pending), FIRST Robotics Tools, Software from our website, and other tools.

The nlpFarm is a Natural Language Processing (NLP) resource where early research prototypes (Java) can evolve into robust and useful open source. Our farmstead collaborates under the OpenNLP initiative, in order to make NLP software publically available.

We want to create a linguistic tool (DTAG) for dependency treebanks and implement algorithms for serial dependency parsing with repair and machine translation, based on probabilistic lexicons learned from mo

A general and small implementation of an artificial neural network in Common Lisp.

FramerD is a distributed semi-structured object database originally developed at MIT. It provides an internationalized Scheme-based scripting language, built-in text analysis tools, and special support for web scripting.

This package contains code for the game of EasyGo, a modified version of the original game of go. This package provides a simple API so that the users can code and test their own players. Thus one can not only play, but also program their own players.

GLD is a traffic flow simulator which can be used to evaluate the performance of AI traffic light controller algorithms and colearning navigation algorithms for cars. It is a discrete simulation which is designed to be easy to expand.

VKAS uses genetic programming methods to find out the relationship among a set of independent and dependent variable. It is a problem solver software which uses evolutionary computing methods. When vkas is run, it creates a population of chromosomes at random. This population is then genetically modified and next population is generated. Each population is subjected to fitness calculation and if a suitable answer chromosome is found then vkas stops and the answer is printed. If a...

Self-replicating automata in continuous two-dimensional space

TIKAPP is becoming a collection of tools for simulation of neural networks. The first available part is an ANSI-C++ library with support for backpropation networks.

RL++ is an easy to use modular open source library for Reinforcement Learning written in C++. It includes learning algorithms (TD, Sarsa, Q) as well as the implementation of value function representations (LookupTable, TileCoding, Neuronal Network).

Kandid generates images using genetic algorithms. In a simulated evolution surprising images can be found calculated with Lisp expressions, Textures, Iterated Function Systems, Linear Cellular Automata, Voroni diagrams, Lindenmayer Systems and POVray

The Parameter Tuning Unity (PTU) aims to adapt the parameters of ever connected multi-agents system, or expert system with a plugged optimization heuristic likes the descent of gradient for instance.