Universal Intelligence: A Definition of Machine Intelligence

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.

[1]  J. Stevens,et al.  Animal Intelligence , 1883, Nature.

[2]  A. Binet,et al.  Méthodes nouvelles pour le diagnostic du niveau intellectuel des anormaux , 1904 .

[3]  A. Binet.  Les Idées modernes sur les enfants , 1910 .

[4]  C. SPEARMAN,et al.  The Measurement of Intelligence , 1927, Nature.

[5]  C. Spearman.  The Abilities of Man their Nature and Measurement , 2020, Nature.

[6]  W. V. Bingham.  Aptitudes and aptitude testing , 1937 .

[7]  L. Thurstone.  Primary mental abilities. , 1938, Science.

[8]  J. Pickova.  The Measurement and Appraisal of Adult Intelligence , 1959 .

[9]  D. Wechsler.  The measurement and appraisal of adult intelligence, 4th ed. , 1958 .

[10]  E. Glover.  DICTIONARY OF PSYCHOLOGY , 1959 .

[11]  E. Boring.  Intelligence as the Tests Test It. , 1961 .

[12]  J. Guilford,et al.  The nature of human intelligence. , 1968 .

[13]  J. Horn.  CHAPTER 16 – Organization of Data on Life-Span Development of Human Abilities , 1970 .

[14]  P. Johnson-Laird,et al.  A theoretical analysis of insight into a reasoning task , 1970 .

[15]  C. Adcock,et al.  Primary Mental Abilities. , 1971, The Journal of general psychology.

[16]  M. A. Merrill,et al.  Stanford-Binet Intelligence Scale , 1972 .

[17]  M. A. Merrill,et al.  Stanford-Binet intelligence scale : manual for the third revision form L-M , 1973 .

[18]  B. Slotnick,et al.  Olfactory Learning-Set Formation in Rats , 1974, Science.

[19]  Allen Newell,et al.  Computer science as empirical inquiry: symbols and search , 1976, CACM.

[20]  John C. Haugland.  Mind Design: Philosophy, Psychology, and Artificial Intelligence , 1981 .

[21]  H. Birx,et al.  The Mismeasure of Man , 1981 .

[22]  N. Block.  Psychologism and Behaviorism , 1981 .

[23]  G. Chaitin.  Gödel's theorem and information , 1982 .

[24]  H. Gardner,et al.  Frames of Mind: The Theory of Multiple Intelligences , 1983 .

[25]  E. Macphail.  Vertebrate intelligence: the null hypothesis , 1985 .

[26]  K. Gunderson.  Mentality and Machines , 1985 .

[27]  M. Minsky.  The Society of Mind , 1986 .

[28]  Richard E. Morehouse.  Beyond IQ: A Triarchic Theory Of Human Intelligence , 1986 .

[29]  R. Cattell.  Intelligence : its structure, growth and action , 1987 .

[30]  Stevan Harnad,et al.  Minds, machines and Searle , 1989, J. Exp. Theor. Artif. Intell..

[31]  John R. Searle,et al.  Minds, brains, and programs , 1980, Behavioral and Brain Sciences.

[32]  R. French.  Subcognition and the Limits of the TuringTest , 1990 .

[33]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[34]  James S. Albus,et al.  Outline for a theory of intelligence , 1991, IEEE Trans. Syst. Man Cybern..

[35]  A. Anastasi.  What Counselors Should Know About the Use and Interpretation of Psychological Tests , 1992 .

[36]  W. Lewis Johnson.  Needed: a new test of intelligence , 1992, SGAR.

[37]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[38]  Stuart M. Shieber,et al.  Lessons from a restricted Turing test , 1994, CACM.

[39]  Cristian S. Calude.  Information and Randomness: An Algorithmic Perspective , 1994 .

[40]  Cristian S. Calude.  Information and Randomness , 1994, Monographs in Theoretical Computer Science An EATCS Series.

[41]  F. Nielsen,et al.  The Bell Curve: Intelligence and Class Structure in American Life. , 1995 .

[42]  F. Hsu,et al.  Deep Blue system overview , 1995, ICS '95.

[43]  D.B. Fogel.  Review of Computational Intelligence: Imitating Life [Book Reviews] , 1995, Proceedings of the IEEE.

[44]  S. Watt.  Naive psychology and the inverted Turing test , 1996 .

[45]  R. Sternberg,et al.  Intelligence: Knowns and unknowns. , 1996 .

[46]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[47]  Jason Hutchens,et al.  How to Pass the Turing Test by Cheating , 1997 .

[48]  T. Zentall.  Animal Memory: The Role of “Instructions” , 1997 .

[49]  William I. Gasarch,et al.  Book Review: An introduction to Kolmogorov Complexity and its Applications Second Edition, 1997 by Ming Li and Paul Vitanyi (Springer (Graduate Text Series)) , 1997, SIGACT News.

[50]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[51]  L. Gottfredson.  Mainstream science on intelligence: An editorial with 52 signatories, history, and bibliography , 1997 .

[52]  T. Zentall,et al.  Shared Attention in Pigeons: Retrieval Failure Does Not Account for the Element Superiority Effect , 1997 .

[53]  L. Gottfredson.  Why g matters: The complexity of everyday life , 1997 .

[54]  Randy Goebel,et al.  Computational intelligence - a logical approach , 1998 .

[55]  David L. Dowe,et al.  A Non-Behavioural, Computational Extension to the Turing Test , 1998 .

[56]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[57]  John McCarthy,et al.  WHAT IS ARTIFICIAL INTELLIGENCE , 1998 .

[58]  Michael C. Pyryt.  Human cognitive abilities: A survey of factor analytic studies , 1998 .

[59]  Matthew V. Mahoney,et al.  Text Compression as a Test for Artificial Intelligence , 1999, AAAI/IAAI.

[60]  A. Paolitto,et al.  Stanford-Binet Intelligence Scale. , 2000 .

[61]  Jason L. Hutchens,et al.  The Developmental Approach to Evaluating Artificial Intelligence — A Proposal , 2000 .

[62]  R. Sternberg,et al.  Handbook of Intelligence , 2000 .

[63]  Ricardo R. Gudwin,et al.  Evaluating intelligence: a computational semiotics perspective , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[64]  J. Raven.  The Raven's Progressive Matrices: Change and Stability over Culture and Time , 2000, Cognitive Psychology.

[65]  J. Sattler.  Assessment of children: Cognitive applications, 4th ed. , 2001 .

[66]  Felix Stalder,et al.  The Age of Spiritual Machines: When Computers Exceed Human Intelligence , 2001, CSOC.

[67]  W. Blattner,et al.  An interview with Dr Terry M. Nett , 2021, Biology of Reproduction.

[68]  Robert J. Sternberg,et al.  Dynamic Testing: The Nature and Measurement of Learning Potential , 2001 .

[69]  AnatTreister-Goren TrainingDepartment,et al.  Creating AI : A Unique Interplay Between the Development of Learning Algorithms and their Education , 2001 .

[70]  Marcus Hutter,et al.  Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions , 2000, ECML.

[71]  Marcus Hutter.  Universal sequential decisions in unknown environments , 2001 .

[72]  J. Sattler.  Assessment of Children: Cognitive Applications , 2001 .

[73]  John A. Horst.  A Native Intelligence Metric for Artificial Systems , 2002 .

[74]  L. Gottfredson.  G: Highly general and highly practical , 2002 .

[75]  S. S. Adams,et al.  Beyond the Turing test: performance metrics for evaluating a computer simulation of the human mind , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[76]  I. Deary.  The general factor of intelligence: how general is it? , 2002 .

[77]  Jürgen Schmidhuber,et al.  The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions , 2002, COLT.

[78]  R. Sternberg,et al.  The general factor of intelligence : how general is it? , 2002 .

[79]  Ofi rNw8x'pyzm,et al.  The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions , 2002 .

[80]  Steffen Christensen,et al.  The Turing Ratio: Metrics For Open-ended Tasks , 2002, GECCO.

[81]  Pei Wang,et al.  On the Working Definition of Intelligence , 2003 .

[82]  José Hernández-Orallo,et al.  A Formal Definition of Intelligence Based on an Intensional Variant of Algorithmic Complexity , 2003 .

[83]  Selmer Bringsjord,et al.  What is Artificial Intelligence? Psychometric AI as an Answer , 2003, IJCAI.

[84]  Ben Goertzel,et al.  Novamente: An Integrative Architecture for General Intelligence , 2004, AAAI Technical Report.

[85]  Paul Schweizer,et al.  The Truly Total Turing Test* , 1998, Minds and Machines.

[86]  A. Kaufman.  Tests of intelligence , 2004 .

[87]  S. Shieber.  Subcognition and the Limits of the Turing Test , 2004 .

[88]  Varol Akman,et al.  Turing Test: 50 Years Later , 2000, Minds and Machines.

[89]  Shane Legg,et al.  A Taxonomy for Abstract Environments. , 2004 .

[90]  Shane Legg,et al.  Ergodic MDPs Admit Self-Optimising Policies , 2004 .

[91]  Marcus Hutter.  Simulation Algorithms for Computational Systems Biology , 2017, Texts in Theoretical Computer Science. An EATCS Series.

[92]  C. S. Wallace,et al.  Statistical and Inductive Inference by Minimum Message Length (Information Science and Statistics) , 2005 .

[93]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[94]  Shane Legg,et al.  A Universal Measure of Intelligence for Artificial Agents , 2005, IJCAI.

[95]  Jason D. Warren,et al.  The Oxford Companion to the Mind , 2005 .

[96]  Marcus Hutter.  General Discounting Versus Average Reward , 2006, ALT.

[97]  Shane Legg,et al.  A Formal Measure of Machine Intelligence , 2006, ArXiv.

[98]  Shane Legg,et al.  Tests of Machine Intelligence , 2006, 50 Years of Artificial Intelligence.

[99]  Shane Legg,et al.  A Collection of Definitions of Intelligence , 2007, AGI.

[100]  Warren D. Smith.  Mathematical definition of"intelligence"(and consequences) , 2006 .

[101]  Marcus Hutter,et al.  Universal Algorithmic Intelligence: A Mathematical Top→Down Approach , 2007, Artificial General Intelligence.

[102]  L. Terman.  The measurement of intelligence , 2007 .

[103]  Marcus Hutter,et al.  On Universal Prediction and Bayesian Confirmation , 2007, Theor. Comput. Sci..

[104]  David L. Dowe,et al.  A computer program capable of passing I.Q. tests , 2008 .

[105]  B. Edmonds.  The social embedding of intelligence: towards producing a machine that could pass the Turing Test , 2008 .

[106]  Paolo Ferragina,et al.  Text Compression , 2009, Encyclopedia of Database Systems.

[107]  Itamar Arel,et al.  Beyond the Turing Test , 2009, Computer.

[108]  Bruce Edmonds,et al.  The Social Embedding of Intelligence , 2009 .