A single ant or bee isn't smart, but their colonies are. The study of swarm intelligence is providing insights that can help humans manage complex systems, from truck routing to military robots.
Memetic Algorithms is a population-based approach for heuristic search in optimization problems. They have shown that they are orders of magnitude faster than traditional Genetic Algorithms for some problem domains.
Department of Mathematical Sciences San Diego State University, Vernor Vinge - Within thirty years, we will have the technological means to create superhuman intelligence. Shortly after, the human era will be ended.
a comprehensive system for designing realistic NPC AI for persistant worlds. It uses a meme metaphor to rationalize the "hows and whys" of NPC life. The Memetic AI Toolkit provides an artificial life designer with a host of tools, documentation, example c
Mazes in general (and hence algorithms to create Mazes) can be organized along seven different classifications. These are: Dimension, Hyperdimension, Topology, Tessellation, Routing, Texture, and Focus.
Developed programmes that apply genetic algorithms to blocks of code/circuits/ideas, instead of starting from a crude framework and building on top of that. Fascinating, logical, and apparently works. in Popular Science
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 dat
a cross-platform C++ framework for rapid AI development. Loom evolved out of the idea that in game development there is often the need for placeholder AI while an application is in initial development phases.
PhysOrg, A pioneering new way of creating computer programs could be used in the future to design and build robots with minds that function like that of a human being, according to a leading researcher at The University of Reading.