Ultimate Cognition à la Gödel

Abstract“All life is problem solving,” said Popper. To deal with arbitrary problems in arbitrary environments, an ultimate cognitive agent should use its limited hardware in the “best” and “most efficient” possible way. Can we formally nail down this informal statement, and derive a mathematically rigorous blueprint of ultimate cognition? Yes, we can, using Kurt Gödel’s celebrated self-reference trick of 1931 in a new way. Gödel exhibited the limits of mathematics and computation by creating a formula that speaks about itself, claiming to be unprovable by an algorithmic theorem prover: either the formula is true but unprovable, or math itself is flawed in an algorithmic sense. Here we describe an agent-controlling program that speaks about itself, ready to rewrite itself in arbitrary fashion once it has found a proof that the rewrite is useful according to a user-defined utility function. Any such a rewrite is necessarily globally optimal—no local maxima!—since this proof necessarily must have demonstrated the uselessness of continuing the proof search for even better rewrites. Our self-referential program will optimally speed up its proof searcher and other program parts, but only if the speed up’s utility is indeed provable—even ultimate cognition has limits of the Gödelian kind.

[1]  Jean-Pierre Bourguignon,et al.  Mathematische Annalen , 1893 .

[2]  Leopold Löwenheim.  Über Möglichkeiten im Relativkalkül , 1915 .

[3]  W. Heisenberg.  Über quantentheoretische Umdeutung kinematischer und mechanischer Beziehungen , 1925 .

[4]  W. Heisenberg.  A quantum-theoretical reinterpretation of kinematic and mechanical relations , 1925 .

[5]  W. Heisenberg.  Über den anschaulichen Inhalt der quantentheoretischen Kinematik und Mechanik , 1927 .

[6]  K. Gödel.  Über formal unentscheidbare Sätze der Principia Mathematica und verwandter Systeme I , 1931 .

[7]  K. Gödel.  Über formal unentscheidbare Sätze der Principia Mathematica und verwandter Systeme I , 1931 .

[8]  A. Kolmogoroff.  Grundbegriffe der Wahrscheinlichkeitsrechnung , 1933 .

[9]  A. Turing.  On computable numbers, with an application to the Entscheidungsproblem , 1937, Proc. London Math. Soc..

[10]  H. Rice.  Classes of recursively enumerable sets and their decision problems , 1953 .

[11]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[12]  E. Feigenbaum,et al.  Computers and Thought , 1963 .

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

[14]  R. Bellman,et al.  V. Adaptive Control Processes , 1964 .

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

[16]  Manuel Blum,et al.  A Machine-Independent Theory of the Complexity of Recursive Functions , 1967, JACM.

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

[18]  Charles H. Moore,et al.  Forth - a language for interactive computing , 1970 .

[19]  Manuel Blum,et al.  On Effective Procedures for Speeding Up Algorithms , 1971, JACM.

[20]  G. Chaitin.  A Theory of Program Size Formally Identical to Information Theory , 1975, JACM.

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

[22]  Douglas R. Hofstadter,et al.  Godel, Escher, Bach: An Eternal Golden Braid , 1981 .

[23]  Douglas B. Lenat,et al.  Theory Formation by Heuristic Search , 1983, Artificial Intelligence.

[24]  H. Cantor.  Ueber eine Eigenschaft des Inbegriffs aller reellen algebraischen Zahlen. , 1984 .

[25]  Leonid A. Levin,et al.  Randomness Conservation Inequalities; Information and Independence in Mathematical Theories , 1984, Inf. Control..

[26]  Paul E. Utgoff,et al.  Shift of bias for inductive concept learning , 1984 .

[27]  Nichael Lynn Cramer,et al.  A Representation for the Adaptive Generation of Simple Sequential Programs , 1985, ICGA.

[28]  John H. Holland,et al.  Properties of the Bucket Brigade , 1985, ICGA.

[29]  William F. Clocksin,et al.  Programming in Prolog , 1987, Springer Berlin Heidelberg.

[30]  Allen Newell,et al.  GPS, a program that simulates human thought , 1995 .

[31]  Jürgen Schmidhuber,et al.  Reinforcement Learning in Markovian and Non-Markovian Environments , 1990, NIPS.

[32]  Toshio Odanaka,et al.  ADAPTIVE CONTROL PROCESSES , 1990 .

[33]  Jürgen Schmidhuber,et al.  Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem , 1990 .

[34]  Konrad Zuse,et al.  Rechnender Raum , 1991, Physik und Informatik.

[35]  Eduardo Sontag,et al.  Turing computability with neural nets , 1991 .

[36]  Jürgen Schmidhuber,et al.  A ‘Self-Referential’ Weight Matrix , 1993 .

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

[38]  R. Penrose,et al.  Shadows of the Mind , 1994 .

[39]  Corso Elvezia.  Discovering Solutions with Low Kolmogorov Complexity and High Generalization Capability , 1995 .

[40]  D. Wolpert,et al.  No Free Lunch Theorems for Search , 1995 .

[41]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[42]  Melvin Fitting,et al.  First-Order Logic and Automated Theorem Proving , 1990, Graduate Texts in Computer Science.

[43]  Wolfgang Banzhaf,et al.  Genetic Programming: An Introduction , 1997 .

[44]  Jürgen Schmidhuber,et al.  Discovering Neural Nets with Low Kolmogorov Complexity and High Generalization Capability , 1997, Neural Networks.

[45]  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.

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

[47]  Jürgen Schmidhuber,et al.  A Computer Scientist's View of Life, the Universe, and Everything , 1999, Foundations of Computer Science: Potential - Theory - Cognition.

[48]  K. Popper.  All life is problem solving , 1997 .

[49]  J. Urgen Schmidhuber.  A Computer Scientist's View of Life, the Universe, and Everything , 1997 .

[50]  Jürgen Schmidhuber,et al.  Reinforcement Learning with Self-Modifying Policies , 1998, Learning to Learn.

[51]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

[52]  C. Koch,et al.  Consciousness and neuroscience. , 1998, Cerebral cortex.

[53]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[54]  Jürgen Schmidhuber,et al.  Algorithmic Theories of Everything , 2000, ArXiv.

[55]  Sepp Hochreiter,et al.  Learning to Learn Using Gradient Descent , 2001, ICANN.

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

[57]  C. L. Giles,et al.  Sequence Learning - Paradigms, Algorithms, and Applications , 2001 .

[58]  Jürgen Schmidhuber,et al.  Sequential Decision Making Based on Direct Search , 2001, Sequence Learning.

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

[60]  Jürgen Schmidhuber,et al.  Hierarchies of Generalized Kolmogorov Complexities and Nonenumerable Universal Measures Computable in the Limit , 2002, Int. J. Found. Comput. Sci..

[61]  Jürgen Schmidhuber,et al.  Bias-Optimal Incremental Problem Solving , 2002, NIPS.

[62]  Marcus Hutter.  The Fastest and Shortest Algorithm for all Well-Defined Problems , 2002, Int. J. Found. Comput. Sci..

[63]  Marcus Hutter,et al.  Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures , 2002, COLT.

[64]  Aaron Sloman,et al.  Virtual Machines and Consciousness , 2003 .

[65]  P. Haikonen.  The Cognitive Approach to Conscious Machines , 2003 .

[66]  Schmidhuber Juergen,et al.  The New AI: General & Sound & Relevant for Physics , 2003 .

[67]  Jürgen Schmidhuber,et al.  Optimal Ordered Problem Solver , 2002, Machine Learning.

[68]  Jürgen Schmidhuber,et al.  Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement , 1997, Machine Learning.

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

[70]  Jürgen Schmidhuber,et al.  Gödel Machines: Towards a Technical Justification of Consciousness , 2005, Adaptive Agents and Multi-Agent Systems.

[71]  Daniel Kudenko,et al.  Adaptive Agents and Multi-Agent Systems II: Adaptation and Multi-Agent Learning , 2003, Adaptive Agents and Multi-Agent Systems.

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

[73]  Jürgen Schmidhuber,et al.  Completely Self-referential Optimal Reinforcement Learners , 2005, ICANN.

[74]  I. Aleksander.  The World in My Mind, My Mind in the World: Key Mechanisms of Consciousness in People, Animals and Machines , 2005 .

[75]  Erkki Oja,et al.  Artificial Neural Networks: Biological Inspirations - ICANN 2005, 15th International Conference, Warsaw, Poland, September 11-15, 2005, Proceedings, Part I , 2005, ICANN.

[76]  J. Schmidhuber.  Don't forget randomness is still just a hypothesis , 2006, Nature.

[77]  Anil K Seth,et al.  Theories and measures of consciousness: an extended framework. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[78]  Jürgen Schmidhuber.  2006: Celebrating 75 Years of AI - History and Outlook: The Next 25 Years , 2006, 50 Years of Artificial Intelligence.

[79]  Jürgen Schmidhuber,et al.  Gödel Machines: Fully Self-referential Optimal Universal Self-improvers , 2007, Artificial General Intelligence.

[80]  Jürgen Schmidhuber,et al.  New Millennium AI and the Convergence of History: Update of 2012 , 2012 .

[81]  B. Baars,et al.  Cognition, Brain, and Consciousness: Introduction to Cognitive Neuroscience , 2007 .

[82]  Martin Volker Butz.  How and Why the Brain Lays the Foundations for a Conscious Self , 2008 .

[83]  Sanjoy Dasgupta,et al.  Adaptive Control Processes , 2010, Encyclopedia of Machine Learning and Data Mining.