• Problems in AI research and how the SP System may help to solve them

    From Gerry Wolff@21:1/5 to All on Thu Nov 12 02:59:31 2020
    Problems in AI research and how the SP System may help to solve them

    The paper "Problems in AI research and how the SP System may help to solve them" (PDF, tinyurl.com/y29yn48p, submitted for publication) [1] describes the clear potential of the SP System (next paragraph) to help solve 19 problems in AI research, most of
    them described in the book Architects of Intelligence by science writer Martin Ford.

    The SP System—meaning the SP Theory of Intelligence and its realisation in the SP Computer Model—is the product of a lengthy programme of research, seeking to simplify and integrate observations and concepts across AI, mainstream computing,
    mathematics, and human learning, perception and cognition. There is an outline description of the SP System in Appendix A of "Problems in AI research”, and more detail in sources referenced in [2].

    A unifying principle in the SP System is information compression via the matching and unification of patterns [3].

    That principle is realised chiefly in the powerful concept of SP-multiple-alignment, borrowed and adapted from the concept of ‘multiple sequence alignment’ in bioinformatics. SP-multiple-alignment is largely responsible for the strengths and
    potential of the SP System across several aspects of AI, and for the seamless integration of diverse aspects of AI, in any combination, the kind of seamless integration that appears to be an essential feature of any AI system that aspires to human-like
    general intelligence.

    Of course, the SP System as it is now is not ‘artificial general intelligence’ (AGI). But I believe the SP System provides a promising foundation for the development of AGI which compares favourably with alternatives.
    I would be happy to try to answer questions, and I would very much value comments about the paper.

    With best wishes,

    Gerry Wolff
    Dr J. Gerard Wolff PhD CEng MIEEE MBCS
    jgw@cognitionresearch.org, +44 (0) 1248 712962, +44 (0) 7746 290775, Twitter: @gerrywolff65, URL: www.cognitionresearch.org.
    [1] A slightly earlier version is archived as arXiv:2009.09079v2 [cs.CY].
    [2] A more detailed description of the SP System is in "The SP Theory of Intelligence: an overview" (PDF, Information, 4 (3), 283-341, 2013, bit.ly/1NOMJ6l) and a much fuller description is in the book Unifying Computing and Cognition: the SP Theory and
    Its Applications. Key papers in the SP programme of research are detailed in Key publications, with notes. And there is more information about publications in the SP programme of research in www.cognitionresearch.org/sp.htm.
    [3] This because of evidence for "Information compression as a unifying principle in human learning, perception, and cognition," Complexity, vol. 2019, Article ID 1879746, 38 pages, 2019, DOI: doi.org/10.1155/2019/1879746 (PDF: bit.ly/2GdIqnY).

    --- SoupGate-Win32 v1.05
    * Origin: fsxNet Usenet Gateway (21:1/5)