Artificial Intelligence

Topics  -> Software Development

Articles   Links

Computer Go Computer Go, the great hard problem in Artificial Intelligence.

Neural Networks

Articles

All Articles in Topic

STEPS TOWARD ARTIFICIAL INTELLIGENCEMarvin The problems of heuristic programming–of making computers solve really difficult problems–are divided into five main areas: Search, Pattern-Recognition, Learning, Planning, and Induction. Wherever appropriate, the discussion is supported by extensive citation of the literature and by descriptions of a few of the most successful heuristic (problem-solving) programs constructed to date.

The creativity machine It writes music, invents soft drinks and dreams up hard materials. The man who built it points the way to immortality

A Proposed Model for Simulating Human Artificial Intelligence Unique Jungian and MBTI approach to develop Human Artificial Intelligence

Eye on the prize By Nils J. Nilsson(1995). AI Magazine 16 (2): 9-17. In its early stages, the field of AI had as its main goal the invention of computer programs having the general problem-solving abilities of humans. Along the way, a major shift of emphasis developed from general-purpose programs toward performance programs, ones whose competence was highly specialized and limited to particular areas of expertise. In this article, Nilsson claims that AI is now at the beginning of another transition, one that will reinvigorate efforts to build programs of general, humanlike competence.

The Rete Matching Algorithm

Computer Chess: The Drosophila of AI

Dots and Boxes en Newsgroups

Complicity and the Brain: Dynamics in Attractor Space This paper outlines a research program that is intended to look for the emergence of consciousness in computers. We argue that a good place to look is the space of Self-Organizing Networks of Attractor Neural Networks (SONofANNs). In the main part of the paper, we then specialize our investigation to Self-Organizing Hopfield Networks (SOHNs), and construct a model that can give rise to emergent semantic networks and brainwave processing, two new concepts introduced here. Finally, we present some ideas about how to carry out the actual search for consciousness.

FOUNDATION FOR INTELLIGENT PHYSICAL AGENTS: FIPA Abstract Architecture Specification The Foundation for Intelligent Physical Agents (FIPA) is an international organization that is dedicated to promoting the industry of intelligent agents by openly developing specifications supporting interoperability among agents and agent-based applications.

Dots-and-Boxes Introduction Dots-and-Boxes (a.k.a. Pigs-and-Sties) is a two player paper-and-pencil game.

Robot SDKs Learn about new software development kits for robots and robotic-enhanced products, including AIBO, Lego Mindstorms, Evolution Robotics and various open source projects.

MENTALIS A forgotten classic game from the 1970’s

Dot And Boxes from Math World A two-person game based on a rectangular lattice of points. Each player, in turn, draws a horizontal or vertical line connecting two adjacent points. Whenever placement of a line complete a single square, the square is colored in, the player scores one point, and the player having completed the square receives an additional move.

Dots & Boxes, and related Mathematical Games by Elwyn Berlekamp Dots and Boxes is a game which children play with pencil and paper.

Stop-Gate This game is taken from the book On Numbers and Games by John Conway (Academic Press, 1976) and is attributed to Goran Andersson.

The World-Wide-Mind: Draft Proposal A change in methodology for the future of AI and Adaptive Behavior research is proposed. It is proposed that researchers construct their agent minds and their agent worlds as servers on the Internet. 3rd parties will use these servers as components in larger systems.

Reinforcement Learning: A Survey This paper surveys the field of reinforcement learning from a computer-science perspective

Vernon Vinge on the Singularity Within thirty years, we will have the technological means to create superhuman intelligence. Shortly after, the human era will be ended.

Co-adaptation in a Team We introduce a cooperative co--evolutionary system to facilitate the development of teams of heterogeneous agents. We believe that k different behavioral strategies for controlling the actions of a group of k agents can combine to form a cooperation strategy which efficiently achieves global goals. We both examine the on--line adaption of behavioral strategies utilizing genetic programming and demonstrate the successful co-evolution of cooperative individuals. (Domain Specific Language DSL)

Cooperative Coevolution of Multi-Agent Systems In certain tasks such as pursuit and evasion, multiple agents need to coordinate their behavior to achieve a common goal. An interesting question is, how can such behavior best be evolved? When the agents are controlled with neural networks, a powerful method is to coevolve them in separate subpopulations, and test together in the common task. In this paper, such a method, called Multi-Agent ESP (Enforced Subpopulations) is presented, and demonstrated in a prey-capture task.

More articles...

Links

All links in topic

The University of Alberta GAMES Group

The Game AI Page These pages are dedicated to the topic of Artificial Intelligence (AI) in games.

AI Magazine Issues Called the "journal of record for the AI community," AI Magazine has been published since 1980. Tables of contents for all issues are available. Abstracts and full-text is also available for all issues (a few articles may not be available because of copyright restrictions).

About AI

Repositorio de IA de Cargenie Mellon University Sistemas, demostraciones, preguntas frecuentes, recursos, sobre todos los temas de Inteligencia Artificial.

Marvin Minsky Marvin Minsky has made many contributions to AI, cognitive psychology, mathematics, computational linguistics, robotics, and optics. In recent years he has worked chiefly on imparting to machines the human capacity for commonsense reasoning.

American Association for Artificial Intelligence Founded in 1979, the American Association for Artificial Intelligence (AAAI) is a nonprofit scientific society devoted to advancing the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines.

The Best of AI Expert

Combinatorial Game Theory Combinatorial Game Theory studies strategies and mathematics of two-player games of perfect knowledge such as chess or go (but often either concentrating instead on simpler games such as nim, or solving endgames and other special cases).

Artificial Intelligence Enlaces sobre Inteligencia Artificial en Open Directory Project

More links...