On Potential Cognitive Abilities in the Machine Kingdom

Animals, including humans, are usually judged on what they could become, rather than what they are. Many physical and cognitive abilities in the ‘animal kingdom’ are only acquired (to a given degree) when the subject reaches a certain stage of development, which can be accelerated or spoilt depending on how the environment, training or education is. The term ‘potential ability’ usually refers to how quick and likely the process of attaining the ability is. In principle, things should not be different for the ‘machine kingdom’. While machines can be characterised by a set of cognitive abilities, and measuring them is already a big challenge, known as ‘universal psychometrics’, a more informative, and yet more challenging, goal would be to also determine the potential cognitive abilities of a machine. In this paper we investigate the notion of potential cognitive ability for machines, focussing especially on universality and intelligence. We consider several machine characterisations (non-interactive and interactive) and give definitions for each case, considering permanent and temporal potentials. From these definitions, we analyse the relation between some potential abilities, we bring out the dependency on the environment distribution and we suggest some ideas about how potential abilities can be measured. Finally, we also analyse the potential of environments at different levels and briefly discuss whether machines should be designed to be intelligent or potentially intelligent.

[1]  Laurent Orseau,et al.  Self-Modification and Mortality in Artificial Agents , 2011, AGI.

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

[3]  R. Solomonoff.  INDUCTIVE INFERENCE RESEARCH STATUS , SPRING 1967 , 1966 .

[4]  L. Levin,et al.  THE COMPLEXITY OF FINITE OBJECTS AND THE DEVELOPMENT OF THE CONCEPTS OF INFORMATION AND RANDOMNESS BY MEANS OF THE THEORY OF ALGORITHMS , 1970 .

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

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

[7]  Laurent Orseau,et al.  Delusion, Survival, and Intelligent Agents , 2011, AGI.

[8]  T R THORP,et al.  Predicting potential intelligence. , 1959, Journal of clinical psychology.

[9]  J. Hernández-Orallo,et al.  IQ tests are not for machines, yet , 2012 .

[10]  Shane Legg,et al.  An Approximation of the Universal Intelligence Measure , 2011, Algorithmic Probability and Friends.

[11]  David L. Dowe,et al.  Foreword re C. S. Wallace , 2008, Comput. J..

[12]  R. Cattell,et al.  Refinement and test of the theory of fluid and crystallized general intelligences. , 1966, Journal of educational psychology.

[13]  David L. Dowe,et al.  Minimum Message Length and Kolmogorov Complexity , 1999, Comput. J..

[14]  M. Tomasello,et al.  The Structure of Individual Differences in the Cognitive Abilities of Children and Chimpanzees , 2010, Psychological science.

[15]  George Barmpalias,et al.  Universality probability of a prefix-free machine , 2012, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[16]  C. S. Wallace,et al.  An Information Measure for Classification , 1968, Comput. J..

[17]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..

[18]  Ray J. Solomonofi.  INDUCTIVE INFERENCE RESEARCH STATUS, SPRING 1967 , 1967 .

[19]  Samson Abramsky,et al.  The foundations of computation, physics and mentality: the Turing legacy , 2012, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[20]  Ray J. Solomonoff,et al.  Complexity-based induction systems: Comparisons and convergence theorems , 1978, IEEE Trans. Inf. Theory.

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

[22]  Peter Grünwald,et al.  Invited review of the book Statistical and Inductive Inference by Minimum Message Length , 2006 .

[23]  Michael Kearns,et al.  Near-Optimal Reinforcement Learning in Polynomial Time , 2002, Machine Learning.

[24]  David L. Dowe,et al.  A computational extension to the Turing test , 1997 .

[25]  A R MAHRER.  Potential intelligence: a learning theory approach to description and clinical implication. , 1958, The Journal of general psychology.

[26]  Joel Veness,et al.  A Monte-Carlo AIXI Approximation , 2009, J. Artif. Intell. Res..

[27]  Gregory J. Chaitin,et al.  A recent technical report , 1974, SIGA.

[28]  Master Gardener,et al.  Mathematical games: the fantastic combinations of john conway's new solitaire game "life , 1970 .

[29]  B. Jack Copeland,et al.  The Turing Test* , 2000, Minds and Machines.

[30]  David L. Dowe,et al.  Refinements of MDL and MML Coding , 1999, Comput. J..

[31]  José Hernández-Orallo,et al.  Measuring Cognitive Abilities of Machines , Humans and Non-Human Animals in a Unified Way : towards Universal Psychometrics , 2012 .

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

[33]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[34]  C. Allen,et al.  Stanford Encyclopedia of Philosophy , 2011 .

[35]  Shane Legg,et al.  Universal Intelligence: A Definition of Machine Intelligence , 2007, Minds and Machines.

[36]  José Hernández-Orallo,et al.  Measuring universal intelligence: Towards an anytime intelligence test , 2010, Artif. Intell..

[37]  Jonathan Schaeffer,et al.  Checkers Is Solved , 2007, Science.

[38]  David L. Dowe,et al.  MML, hybrid Bayesian network graphical models, statistical consistency, invarianc , 2010 .

[39]  José Hernández-Orallo,et al.  On the Computational Measurement of Intelligence Factors , 2011 .

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

[41]  José Hernández-Orallo,et al.  Comparing Humans and AI Agents , 2011, AGI.

[42]  M. Tomasello,et al.  Humans Have Evolved Specialized Skills of Social Cognition: The Cultural Intelligence Hypothesis , 2007, Science.

[43]  José Hernández-Orallo,et al.  On More Realistic Environment Distributions for Defining, Evaluating and Developing Intelligence , 2011, AGI.

[44]  Ben Goertzel,et al.  AGI Preschool: A Framework for Evaluating Early-Stage Human-like AGIs , 2009 .

[45]  Marcus Hutter,et al.  Universal Artificial Intellegence - Sequential Decisions Based on Algorithmic Probability , 2005, Texts in Theoretical Computer Science. An EATCS Series.

[46]  A. Kolmogorov.  Three approaches to the quantitative definition of information , 1968 .

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

[48]  Gregory J. Chaitin,et al.  On the Length of Programs for Computing Finite Binary Sequences , 1966, JACM.

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

[50]  S. Legg,et al.  Machine super intelligence , 2008 .

[51]  Kent G. Bailey,et al.  Potential Intelligence or Intelligence Test Potential?: A Question of Empirical Validity. , 1972 .

[52]  C. Gallistel,et al.  The learning curve: implications of a quantitative analysis. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[53]  C. Q. Lee,et al.  The Computer Journal , 1958, Nature.

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

[55]  José Hernández-Orallo,et al.  On Evaluating Agent Performance in a Fixed Period of Time (Extended Version) , 2010, AGI 2010.

[56]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[57]  C. E. M. JOAD,et al.  Aristotle's Metaphysics. , 1925, Nature.

[58]  José Hernández-Orallo,et al.  Evaluating a Reinforcement Learning Algorithm with a General Intelligence Test , 2011, CAEPIA.

[59]  José Hernández-Orallo,et al.  Turing Tests with Turing Machines , 2012, Turing-100.

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

[61]  R. J. Solomon Off,et al.  The time scale of artificial intelligence: Reflections on social effects , 1985 .

[62]  Shun-ichi Amari,et al.  Four Types of Learning Curves , 1992, Neural Computation.