Computing as compression: the SP theory of intelligence

Abstract

This paper provides an overview of the SP theory of intelligence and its central idea that artificial intelligence, mainstream computing, and much of human perception and cognition, may be understood as information compression. The background and origins of the SP theory are described, and the main elements of the theory, including the key concept of multiple alignment, borrowed from bioinformatics but with important differences. Associated with the SP theory is the idea that redundancy in information may be understood as repetition of patterns, that compression of information may be achieved via the matching and unification (merging) of patterns, and that computing and information compression are both fundamentally probabilistic. It appears that the SP system is Turing-equivalent in the sense that anything that may be computed with a Turing machine may, in principle, also be computed with an SP machine. One of the main strengths of the SP theory and the multiple alignment concept is in modelling concepts and phenomena in artificial intelligence. Within that area, the SP theory provides a simple but versatile means of representing different kinds of knowledge, it can model both the parsing and production of natural language, with potential for the understanding and translation of natural languages, it has strengths in pattern recognition, with potential in computer vision, it can model several kinds of reasoning, and it has capabilities in planning, problem solving, and unsupervised learning. The paper includes two examples showing how alternative parsings of an ambiguous sentence may be modelled as multiple alignments, and another example showing how the concept of multiple alignment may be applied in medical diagnosis.