Search

This book develops the conjecture that all kinds of information processing in computers and in brains may usefully be understood as "information compression by multiple alignment, unification and search". This "SP theory", which has been under development since 1987, provides a unified view of such things as the workings of a universal Turing machine, the nature of 'knowledge', the interpretation and production of natural language, pattern recognition and best-match information retrieval, several kinds of probabilistic reasoning, planning and problem solving, unsupervised learning, and a range of concepts in mathematics and logic. The theory also provides a basis for the design of an 'SP' computer with several potential advantages compared with traditional digital computers.

This paper describes a novel approach to grammar induction that has been developed within a framework designed to integrate learning with other aspects of computing, AI, mathematics and logic. This framework, called "information compression by multiple alignment, unification and search" (ICMAUS), is founded on principles of Minimum Length Encoding pioneered by Solomonoff and others. Most of the paper describes SP70, a computer model of the ICMAUS framework that incorporates processes for unsupervised learning of grammars. An example is presented to show how the model can infer a plausible grammar from appropriate input. Limitations of the current model and how they may be overcome are briefly discussed.

The SP theory of computing and cognition, described in previous publications, is an attractive model for intelligent databases because it provides a simple but versatile format for different kinds of knowledge, it has capabilities in artificial intelligence, and it can also function like established database models when that is required. This paper describes how the SP model can emulate other models used in database applications and compares the SP model with those other models. The artificial intelligence capabilities of the SP model are reviewed and its relationship with other artificial intelligence systems is described. Also considered are ways in which current prototypes may be translated into an 'industrial strength' working system.

This article introduces the conjecture that "mathematics, logic and related disciplines may usefully be understood as information compression (IC) by 'multiple alignment', 'unification' and 'search' (ICMAUS)". As a preparation for the two main sections of the article, concepts of information and information compression are reviewed. Related areas of research are also described including IC in brains and nervous systems, and IC in relation to inductive inference, Minimum Length Encoding and probabilistic reasoning. The ICMAUS concepts and a computer model in which they are embodied are briefly described. The first of the two main sections describes how many of the commonly-used forms and structures in mathematics, logic and related disciplines (such as theoretical linguistics and computer programming) may be seen as devices for IC. In some cases, these forms and structures may be interpreted in terms of the ICMAUS framework. The second main section describes a selection of examples where processes of calculation and inference in mathematics, logic and related disciplines may be understood as IC. In many cases, these examples may be understood more specifically in terms of the ICMAUS concepts.

This paper describes an approach to the representation and processing of ontologies in the Semantic Web, based on the ICMAUS theory of computation and AI. This approach has strengths that complement those of languages based on the Resource Description Framework (RDF) such as RDF Schema and DAML+OIL. The main benefits of the ICMAUS approach are simplicity and comprehensibility in the representation of ontologies, an ability to cope with errors and uncertainties in knowledge, and a versatile reasoning system with capabilities in the kinds of probabilistic reasoning that seem to be required in the Semantic Web.

This paper describes how the elements of the SP theory (Wolff, 2003a) may be realised with neural structures and processes. To the extent that this is successful, the insights that have been achieved in the SP theory - the integration and simplification of a range of phenomena in perception and cognition - may be incorporated in a neural view of brain function. These proposals may be seen as a development of Hebb's (1949) concept of a 'cell assembly'. By contrast with that concept and variants of it, the version described in this paper proposes that any one neuron can belong in one assembly and only one assembly. A distinctive feature of the present proposals is that any neuron or cluster of neurons within a cell assembly may serve as a proxy or reference for another cell assembly or class of cell assemblies. This device provides solutions to many of the problems associated with cell assemblies, it allows information to be stored in a compressed form, and it provides a robust mechanism by which assemblies may be connected to form hierarchies, grammars and other kinds of knowledge structure. Drawing on insights derived from the SP theory, the paper also describes how unsupervised learning may be achieved with neural structures and processes. This theory of learning overcomes weaknesses in the Hebbian concept of learning and it is, at the same time, compatible with the observations that Hebb's theory was designed to explain., Comment: This is a radical revision with new content which is shorter and, I hope, clearer

This article presents an overview of the idea that "information compression by multiple alignment, unification and search" (ICMAUS) may serve as a unifying principle in computing (including mathematics and logic) and in such aspects of human cognition as the analysis and production of natural language, fuzzy pattern recognition and best-match information retrieval, concept hierarchies with inheritance of attributes, probabilistic reasoning, and unsupervised inductive learning. The ICMAUS concepts are described together with an outline of the SP61 software model in which the ICMAUS concepts are currently realised. A range of examples is presented, illustrated with output from the SP61 model.

This article introduces the idea that "information compression by multiple alignment, unification and search" (ICMAUS) provides a framework within which natural language syntax may be represented in a simple format and the parsing and production of natural language may be performed in a transparent manner. The ICMAUS concepts are embodied in a software model, SP61. The organisation and operation of the model are described and a simple example is presented showing how the model can achieve parsing of natural language. Notwithstanding the apparent paradox of 'decompression by compression', the ICMAUS framework, without any modification, can produce a sentence by decoding a compressed code for the sentence. This is illustrated with output from the SP61 model. The article includes four other examples - one of the parsing of a sentence in French and three from the domain of English auxiliary verbs. These examples show how the ICMAUS framework and the SP61 model can accommodate 'context sensitive' features of syntax in a relatively simple and direct manner.

This paper argues that the operations of a 'Universal Turing Machine' (UTM) and equivalent mechanisms such as the 'Post Canonical System' (PCS) - which are widely accepted as definitions of the concept of `computing' - may be interpreted as *information compression by multiple alignment, unification and search* (ICMAUS). The motivation for this interpretation is that it suggests ways in which the UTM/PCS model may be augmented in a proposed new computing system designed to exploit the ICMAUS principles as fully as possible. The provision of a relatively sophisticated search mechanism in the proposed 'SP' system appears to open the door to the integration and simplification of a range of functions including unsupervised inductive learning, best-match pattern recognition and information retrieval, probabilistic reasoning, planning and problem solving, and others. Detailed consideration of how the ICMAUS principles may be applied to these functions is outside the scope of this article but relevant sources are cited in this article.

This article introduces the idea that probabilistic reasoning (PR) may be understood as "information compression by multiple alignment, unification and search" (ICMAUS). In this context, multiple alignment has a meaning which is similar to but distinct from its meaning in bio-informatics, while unification means a simple merging of matching patterns, a meaning which is related to but simpler than the meaning of that term in logic. A software model, SP61, has been developed for the discovery and formation of 'good' multiple alignments, evaluated in terms of information compression. The model is described in outline. Using examples from the SP61 model, this article describes in outline how the ICMAUS framework can model various kinds of PR including: PR in best-match pattern recognition and information retrieval; one-step 'deductive' and 'abductive' PR; inheritance of attributes in a class hierarchy; chains of reasoning (probabilistic decision networks and decision trees, and PR with 'rules'); geometric analogy problems; nonmonotonic reasoning and reasoning with default values; modelling the function of a Bayesian network.

This paper describes a novel approach to unsupervised learning that has been developed within a framework of "information compression by multiple alignment, unification and search" (ICMAUS), designed to integrate learning with other AI functions such as parsing and production of language, fuzzy pattern recognition, probabilistic and exact forms of reasoning, and others., Comment: 39 pages, 1 JPEG figure