9 projects tagged "Artificial Intelligence"
EAsea Specification of Evolutionary Algorithms (EASEA), is a high-level language dedicated to the specification of evolutionary algorithms. The language and compiler are quite mature. EASEA compiles .ez specification files into C++ or Java object files, using existing evolutionary libraries. Supported C++ libraries currently are GALib or EO.
The Robot Auto Racing Simulator (RARS) consists of a simulation of the physics of cars racing on a track, a graphic display of the race, and a separate control program (robot "driver") for each car. The goal of the game is to implement such a control program in order to compete against other programmers. An official formula one season is held every year.
Trans (short for Transmuter Programming Language) is an extremely dynamic, biologically-inspired prototyping language providing a framework for experimenting with naturally evolving systems of objects over the net, and for exploring new ideas about recombinant software, code morphing, and evolutionary programming. Trans is also a very capable general-purpose programming language. It's fast, flexible, compact, object-oriented, highly extensible, and easy-to-learn. It can be used for rapid prototyping, or as a scripting language, an embedded language, a network server or client, a system of cooperating network nodes, a real-time control and monitoring system, and more.
Turing Machine (C++ Implementation) is a Turing machine simulation that is defined by a series of input files. These include a metafile containing data related to some Turing machine, a states file containing a list of initial, halting, and internal states, an alphabet file of empty, input, and internal symbols, a transition file of transition rules, and input word files, which detail the input given on a tape.
ca-ga is a toy artificial life simulation that uses genetic algorithms on large cellular automata. It uses simple but easily extended DNA that is 8k long by default, though you can take the size out to anything you have time to evolve. It sits under each cell of a 128x128 board and orders operations to transfer energy in the hopes of achieving a kill and breed. The simulation features a mutating fitness function, emergent sex, and a proof of concept real world fitness function. After enough generations, the cells or genes could achieve collectivism and organismhood, coordinating the values of the hotspots that determine board temperature in order to maintain a desired equilibrium. But maybe not. If you work in a fitness function, an optimizing problem solver results.