Bibliographic Details
| Title: |
Knowledge Discovery in Deep Blue. |
| Authors: |
Campbell, Murray1 mcam@us.ibm.com |
| Source: |
Communications of the ACM. Nov99, Vol. 42 Issue 11, p65-67. 3p. |
| Subjects: |
Deep Blue (Computer), IBM computers, Databases, World Chess Championship, Chess, Computer systems |
| Abstract: |
A vast database of human experience can be used to direct a search. 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 involving large databases expert decisions. Deep Blue uses knowledge extracted from a Grandmaster game database to improve its performance in actual play. The extended book technique, involving summarized human decisions to bias a search, also appears to be of general value in non-chess domains with access to large databases of expert decisions, such as other games, medical diagnosis and stock trading, especially when there is a useful similarity measure between differing situations for a given domain. |
| Database: |
Engineering Source |
