Machine Methods for Acquiring, Learning, and Applying Knowledge.
Saved in:
| Title: | Machine Methods for Acquiring, Learning, and Applying Knowledge. |
|---|---|
| Language: | English |
| Authors: | Hayes-Roth, Frederick, Rand Corp., Santa Monica, CA. |
| Availability: | The Rand Corporation, 1700 Main Street, Santa Monica, California 90406 ($5.00 per copy) |
| Peer Reviewed: | N |
| Page Count: | 84 |
| Publication Date: | 1978 |
| Document Type: | Reports - Descriptive |
| Descriptors: | Artificial Intelligence, Automation, Computer Oriented Programs, Cybernetics, Game Theory, Information Processing, Programing, Research Proposals |
| Abstract: | A research plan for identifying and acting upon constraints that impede the development of knowledge-based intelligent systems is described. The two primary problems identified are knowledge programming, the task of which is to create an intelligent system that does what an expert says it should, and learning, the problem requiring the criticizing and expanding of current knowledge to improve overall system performance. In this view, learning produces new knowledge which must be accommodated to implement an improved system. Motivating problems, technical requirements for supporting system extensibility and improvability, and research proposed to achieve these objectives are described and related to previous research. Numerous examples are drawn for a heuristic program that plays a moderately difficult card game (hearts). Several appendices provide additional details on many technical issues, including the representation of knowledge and the structure of knowledge bases, the design of a knowledge programmer, various control methods, the design of a learning workbench, an illustrative learning scenario, and various learning heuristics. (Author) |
| Entry Date: | 1980 |
| Accession Number: | ED178060 |
| Database: | ERIC |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: eric DbLabel: ERIC An: ED178060 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Machine Methods for Acquiring, Learning, and Applying Knowledge. – Name: Language Label: Language Group: Lang Data: English – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Hayes-Roth%2C+Frederick%22">Hayes-Roth, Frederick</searchLink><br /><searchLink fieldCode="AR" term="%22Rand+Corp%2E%2C+Santa+Monica%2C+CA%2E%22">Rand Corp., Santa Monica, CA.</searchLink> – Name: Avail Label: Availability Group: Avail Data: The Rand Corporation, 1700 Main Street, Santa Monica, California 90406 ($5.00 per copy) – Name: PeerReviewed Label: Peer Reviewed Group: SrcInfo Data: N – Name: Pages Label: Page Count Group: Src Data: 84 – Name: DatePubCY Label: Publication Date Group: Date Data: 1978 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Reports - Descriptive – Name: Subject Label: Descriptors Group: Su Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Automation%22">Automation</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Oriented+Programs%22">Computer Oriented Programs</searchLink><br /><searchLink fieldCode="DE" term="%22Cybernetics%22">Cybernetics</searchLink><br /><searchLink fieldCode="DE" term="%22Game+Theory%22">Game Theory</searchLink><br /><searchLink fieldCode="DE" term="%22Information+Processing%22">Information Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Programing%22">Programing</searchLink><br /><searchLink fieldCode="DE" term="%22Research+Proposals%22">Research Proposals</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: A research plan for identifying and acting upon constraints that impede the development of knowledge-based intelligent systems is described. The two primary problems identified are knowledge programming, the task of which is to create an intelligent system that does what an expert says it should, and learning, the problem requiring the criticizing and expanding of current knowledge to improve overall system performance. In this view, learning produces new knowledge which must be accommodated to implement an improved system. Motivating problems, technical requirements for supporting system extensibility and improvability, and research proposed to achieve these objectives are described and related to previous research. Numerous examples are drawn for a heuristic program that plays a moderately difficult card game (hearts). Several appendices provide additional details on many technical issues, including the representation of knowledge and the structure of knowledge bases, the design of a knowledge programmer, various control methods, the design of a learning workbench, an illustrative learning scenario, and various learning heuristics. (Author) – Name: DateEntry Label: Entry Date Group: Date Data: 1980 – Name: AN Label: Accession Number Group: ID Data: ED178060 |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED178060 |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: English PhysicalDescription: Pagination: PageCount: 84 Subjects: – SubjectFull: Artificial Intelligence Type: general – SubjectFull: Automation Type: general – SubjectFull: Computer Oriented Programs Type: general – SubjectFull: Cybernetics Type: general – SubjectFull: Game Theory Type: general – SubjectFull: Information Processing Type: general – SubjectFull: Programing Type: general – SubjectFull: Research Proposals Type: general Titles: – TitleFull: Machine Methods for Acquiring, Learning, and Applying Knowledge. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Rand Corp., Santa Monica, CA. – PersonEntity: Name: NameFull: Hayes-Roth, Frederick IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Type: published Y: 1978 |
| ResultId | 1 |
