The SP Theory of Intelligence: An Overview

This article is an overview of the SP theory of intelligence, which aims to simplify and integrate concepts across artificial intelligence, mainstream computing and human perception and cognition, with information compression as a unifying theme. It is conceived of as a brain-like system that receives "New" information and stores some or all of it in compressed form as "Old" information; and it is realised in the form of a computer model, a first version of the SP machine. The matching and unification of patterns and the concept of multiple alignment are central ideas. Using heuristic techniques, the system builds multiple alignments that are "good" in terms of information compression. For each multiple alignment, probabilities may be calculated for associated inferences. Unsupervised learning is done by deriving new structures from partial matches between patterns and via heuristic search for sets of structures that are "good" in terms of information compression. These are normally ones that people judge to be "natural", in accordance with the "DONSVIC" principle—the discovery of natural structures via information compression. The SP theory provides an interpretation for concepts and phenomena in several other areas, including "computing", aspects of mathematics and logic, the representation of knowledge, natural language processing, pattern recognition, several kinds of reasoning, information storage and retrieval, planning and problem solving, information compression, neuroscience and human perception and cognition. Examples include the parsing and production of language with discontinuous dependencies in syntax, pattern recognition at multiple levels of abstraction and its integration with part-whole relations, nonmonotonic reasoning and reasoning with default values, reasoning in Bayesian networks, including "explaining away", causal diagnosis, and the solving of a geometric analogy problem.