Knowledge discovery in deep blue

  title={Knowledge discovery in deep blue},
  author={Murray Campbell},
  journal={Communications of the ACM},
  pages={65 - 67}
  • Murray Campbell
  • Published 1 November 1999
  • Computer Science
  • Communications of the ACM
Deep Blue was the first chess computer to defeat a reigning human world chess champion in a regulation match. A number of factors contributed to the system's success, including its ability to extract useful knowledge from a database of 700,000 Grandmaster chess games—a process that has implications for any non-chess knowledge-discovery application involv-A vast database of human experience can be used to direct a search. 

Figures from this paper

Deep Blue

Hydra: Report and technical overview

This paper presents a review on the chess program Hydra, on a technical level as well as from a social perspective, which clearly crossed the 3000 Elo mark, ahead of all other machines and human players.

Machine Learning in Computer Chess: Genetic Programming and KRK

This paper describes genetic programming as a machine learning paradigm and evaluates its results in attempting to learn basic chess rules and shows promising results in spite of a lack of significant chess knowledge.

Investigations into Playing Chess Endgames using Reinforcement Learning.

The results suggests that, even though the agents faced a highly information sparse environment, an agent using a well selected view of the state information was still able to learn to not only to differentiate between various terminating board positions but also to improve its play against a random player.

Comparing Typical Opening Move Choices Made by Humans and Chess Engines

There is a strong association between humans' and machines' choices of opening moves when using a book to guide their choices in human versus human competitions.

Learning to Play Strong Poker

This chapter describes and evaluates the implicit and explicit learning in the poker program LOKI, a program capable of playing reasonably strong poker, but there remains considerable research to be done to play at a world-class level.

Machine learning in games: a survey

This paper provides a survey of previously published work on machine learning in game playing around a variety of problems that typically arise in gamePlaying and that can be solved with machine learning methods.

Investigating evolutionary checkers by incorporating individual and social learning, N-tuple systems and a round robin tournament

Artificial neural networks are employed to evolve game playing strategies for the game of checkers by introducing a league structure into the learning phase of a system based on Blondie24, and it is believed that this helps eliminate some of the randomness in the evolution.

AlphaDDA: game artificial intelligence with dynamic difficulty adjustment using AlphaZero

This study shows thatAlphaDDA can balance its skill with that of the other AI agents, except for a random player, and believes that the AlphaDDA approach can be used for any game in which the DNN can estimate the value from the state.

Playing Games with Theorem Provers-- Content Areas : Game Playing , Automated Reasoning , Theorem Proving

  • Computer Science
  • 2005
The use of a logic based language to describe games and a game playing system, named Monster, built from an automated theorem prover are described.



IBM's Deep Blue Chess grandmaster chips

The design philosophy, general architecture, and performance of the chess chips, which provided most of Deep Blue's computational power, are described.