Towards Domain-Independent Machine Intelligence

Adaptive predictive search (APS), is a learning system framework, which given little initial domain knowledge, increases its decision-making abilities in complex problems domains. In this paper we give an entirely domain-independent version of APS that we are implementing in the PEIRCE conceptual graphs workbench. By using conceptual graphs as the \base language" a learning system is capable of re ning its own pattern language for evaluating states in the given domain that it nds itself in. In addition to generalizing APS to be domain-independent and CG-based we describe fundamental principles for the development of AI systems based on the structured pattern approach of APS. It is hoped that this e ort will lead the way to a more principled, and well-founded approach to the problems of mechanizing machine intelligence. The APS frameworkhas beenappliedto a numberof complexproblemdomains(includingchess, othello, pente and image alignment) where the combinatorics of the state space ...

• Type: Conference
• Year: 1993
• Where: ICCS
• Authors: Robert Levinson
• Keywords: Applied Computing, APS Chess Sytem, Conceptual Graphs, ICCS 1993, PEIRCE Conceptual Graphs