Use this URL to cite or link to this record in EThOS:
Title: Artificial learning
Author: Knapman, John
Awarding Body: University of Edinburgh
Current Institution: University of Edinburgh
Date of Award: 1978
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Principles of learning are presented and a program that embodies them is described. It works in a simple domain, involving printing on a teletypewriter and conducting a dialogue about what happens, but the principles are apparently much more general. They are related to psychological notions of long and short term memory. These are defined here in strictly computational terms, based on the ideas of control structure and run-time, structure. The learning mechanism is intimately bound up with the nature of the memory constructs. The principles are applied to examples of word meaning, grammar and causality and the program learns to use a relative clause, temporal relations and the past tense, as well as doing some work with number. The relevance to Piaget's theories is discussed. The research has a bearing on previous work in natural language processing, cognition and memory. In particular, the doctrine of procedural representation of knowledge is followed. Objects resembling frames emerge naturally from the way memory is organised. Searches are strictly limited and combinatorial explosions do not arise. The work is seen as an alternative to the customary approaches to automatic programming.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available