Projects tagged ‘ai’ and ‘genetic’

Watchmaker is an extensible, high-performance, multi-threaded, object-oriented framework for implementing platform-independent evolutionary computation (genetic algorithms, etc.) in Java. The ... [More] evolution engine operates on POJOs (Plain Old Java Objects) and does not require that evolved objects extend a specific base class nor implement any particular interfaces. This decoupling of framework and application code is achieved via a clean, generics-enabled API and without the need for expensive runtime reflection. [Less]

Traveling Salesman Problem - Java Genetic Algorithm Solution Binary/Source/SVN/Documentation available. Application features Implementation and comparison of different genetic algorithms - ... [More] unisex random mutation - crossover algorithm - 2opt heuristics + unisex random mutation - 2opt heuristics + crossover algorithm Open source multi platform Java application with well commented source code Console and GUI application mode Parametrized configuration Multi threading computation engine Application thread priority settings Simple map file formats, exporting existing maps, using external maps - map of 192 real cities from CZ, coordinates in S-JTSK, distances in meters - fractal maps (circle, triangle, square, spiral, ... ) Descriptive XML and PDF reports, converting XML reports to PDF Web support General genetic algorithm problems Code the problem Define fitness function Select genetic algorithm engine (population and mutation handling, multithreading) Use good mutation algorithm to create offspring Implement random mutations Think about using heuristics Apply the right initial parameters (population size, mutation ratio, population growth) Initialize population Run the computation on proper hardware Links Definition and research of Traveling Salesman Problem http://www.tsp.gatech.edu/ Basic description of genetic algorithms http://en.wikipedia.org/wiki/Genetic_algorithm Suggested and probably best way for solving TSP using genetic algorithm and 2opt heuristic optimization described by Hiroaki Sengoku and Ikuo Yoshihara http://www.gcd.org/sengoku/docs/arob98.pdf [Less]

Pyevolve was developed to be a complete genetic algorithm framework written in pure python.

The dANN project is a library to help facilitate artificial neural networks within other applications. It is currently written in Java, C++, and C#. However only the java version is currently in ... [More] active development. If you want to obtain a version other than the java version you will need to get it directly from SVN. Our intentions are two fold. First, to provide a powerful interface for programs to include conventional artificial neural network technology into their code. Second, To act as a testing ground for research and development of new AI concepts. We provide new AI technology we have developed, and the latest algorithms already on the market. In the spirit of modular programming the library also provides access to the primitive components giving you greater control. [Less]

Genetic Star Fighter is a very simple game made in Ruby with the Gosu 2D game library. The game is just an excuse to visualize the undergoing process, which is the enemy's code improvement through ... [More] evolution. Our goal is to learn about Evolutionary Computing as we go, and not to make an impressive game (just an impressive AI). The mission is quite simple: you are a Star Fighter and your job is to push out of the map as many other Star Fighters as you can. [Less]

MOORPH is an artificial embryogeny system for specifying and evolving 3D structures. Genomes are encoded as XML structures, which can then be translated, through a developmental process, into 3D morphologies.

simple java genetic library

GPath is an evolutionary graph search algorithm that tries to solve the single-source shortest path problem for a graph, in which each node has a coordinate attached. It's based on the idea of ... [More] chemotaxis, the method by which many single and multi-cellular organisms find their food. [Less]

PyGression GP is a symbolic regression system written in Python using genetic programming techniques. It's inspired by TinyGP, a highly optimised GP system that was originally developed to meet the ... [More] specifications set out in the TinyGP competition of the Genetic and Evolutionary Computation Conference (GECCO) 2004. Start here to know what is all about: PyGression GPRationale: Why are we doing this?What is Symbolic Regression?What are Evolutionary Algorithms?What does Symbolic Regression have to do with Evolutionary Algorithms?Design Overview [Less]