Towards domain-independent machine intelligence

Abstract

Adaptive predictive search (APS), is a learning system frame-work, 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 refining its own pattern language for evaluating states in the given domain that it finds 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 effort will lead the way to a more principled, and well-founded approach to the problems of mechanizing machine intelligence.

The APS framework has been applied to a number of complex problem domains (including chess, Othello, pente and image alignment) where the combinatorics of the state space is large and the learning process only receives reinforcement at the end of each search. The unique features of the APS framework are its pattern-weight representation of control knowledge and its integration of several learning techniques including temporal difference learning, simulated annealing, and genetic algorithms. Morph, an APS chess sytem, is now being translated into PEIRCE.