Universal intelligence: A definition of machine intelligence

Shane Legg*, Marcus Hutter

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    419 Citations (Scopus)

    Abstract

    A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: we take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

    Original languageEnglish
    Pages (from-to)391-444
    Number of pages54
    JournalMinds and Machines
    Volume17
    Issue number4
    DOIs
    Publication statusPublished - Dec 2007

    Fingerprint

    Dive into the research topics of 'Universal intelligence: A definition of machine intelligence'. Together they form a unique fingerprint.

    Cite this