2012/12/02 by J. Gerard Wolff, Wolff, James Gerard
Biochemistry, Genetics and Molecular Biology · Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Biomedical Text Mining and Ontologies #Cognitive Computing and Networks #Computability, Logic, AI Algorithms #Computation and Language (cs.CL) #Data Quality and Management #FOS: Computer and information sciences #Scientific Computing and Data Management
paper · pdf · doi:10.48550/arxiv.1212.0229
openalex publication_date 2012/12/02 · openalex created_date 2022/08/31 · openalex updated_date 2026/07/28
The main purpose of this article is to describe potential benefits and\napplications of the SP theory, a unique attempt to simplify and integrate ideas\nacross artificial intelligence, mainstream computing and human cognition, with\ninformation compression as a unifying theme. The theory, including a concept of\nmultiple alignment, combines conceptual simplicity with descriptive and\nexplanatory power in several areas including representation of knowledge,\nnatural language processing, pattern recognition, several kinds of reasoning,\nthe storage and retrieval of information, planning and problem solving,\nunsupervised learning, information compression, and human perception and\ncognition. In the SP machine -- an expression of the SP theory which is\ncurrently realised in the form of computer models -- there is potential for an\noverall simplification of computing systems, including software. As a theory\nwith a broad base of support, the SP theory promises useful insights in many\nareas and the integration of structures and functions, both within a given area\nand amongst different areas. There are potential benefits in natural language\nprocessing (with potential for the understanding and translation of natural\nlanguages), the need for a versatile intelligence in autonomous robots,\ncomputer vision, intelligent databases, maintaining multiple versions of\ndocuments or web pages, software engineering, criminal investigations, the\nmanagement of big data and gaining benefits from it, the semantic web, medical\ndiagnosis, the detection of computer viruses, the economical transmission of\ndata, and data fusion. Further development of these ideas would be facilitated\nby the creation of a high-parallel, web-based, open-source version of the SP\nmachine, with a good user interface. This would provide a means for researchers\nto explore what can be done with the system and to refine it.\n