Towards a Functional Architecture for Intelligence Based on Generic Information Processing Tasks

Abstract

The level of abstraction of much of the work in knowledge-based systems (the rule, frame, logic level) is too low to provide a rich enough vocabulary for knowledge and control. I provide an overview of a framework called the Generic Task approach that proposes that knowledge systems should be built out of building blocks, each of which is appropriat e for a basic type of problem solving. Each generic task uses forms of knowledge and control s trategi es th at are characteristic to it, and are generally conceptually closer to domain knowledge. This facilitate s knowledge acquisition, and can produce a more perspicuous explanation of problem solving. The relationship of the constructs at the generic task level to the rule-frame level is analogous to that between high level programming languages and assembly languages. I describe a set of generic tasks that have been found particularly useful in constructing diagnostic, design and planning systems; diagnostic reasoning is used to illustrate the approach. I describe the Generic Task Toolset for constructing knowledge systems, which embodies the Generic Task approach . I conclude with the implications of this approach for the functional architecture of intelligence.