Minds and Machines

, Volume 14, Issue 4, pp 453–484 | Cite as

The Concept of a Universal Learning System as a Basis for Creating a General Mathematical Theory of Learning

  • Yury P. Shimansky

Abstract

The number of studies related to natural and artificial mechanisms of learning rapidly increases. However, there is no general theory of learning that could provide a unifying basis for exploring different directions in this growing field. For a long time the development of such a theory has been hindered by nativists' belief that the development of a biological organism during ontogeny should be viewed as parameterization of an innate, encoded in the genome structure by an innate algorithm, and nothing essentially new is created during this process. Noam Chomsky has claimed, therefore, that the creation of a non-trivial general mathematical theory of learning is not feasible, since any algorithm cannot produce a more complex algorithm. This study refutes the above argumentation by developing a counter-example based on the mathematical theory of algorithms and computable functions. It introduces a novel concept of a Universal Learning System (ULS) capable of learning to control in an optimal way any given constructive system from a certain class. The necessary conditions for the existence of a ULS and its main functional properties are investigated. The impossibility of building an algorithmic ULS for a sufficiently complex class of controlled objects is shown, and a proof of the existence of a non-algorithmic ULS based on the axioms of classical mathematics is presented. It is argued that a non-algorithmic ULS is a legitimate object of not only mathematics, but also the world of nature. These results indicate that an algorithmic description of the organization and adaptive development of biological systems in general is not sufficient. At the same time, it is possible to create a rigorous non-algorithmic general theory of learning as a theory of ULS. The utilization of this framework for integrating learning-related studies is discussed.

computability creativity physical constructiveness recursive function theory theory of learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Amari,S.(1991),'Mathematical Theory of Neural Learning',New Generation Computing 8, pp.281-294.Google Scholar
  2. Baev, K.V.and Shimansky, Y.P.(1992),'Principles of Organization of Neural Systems Controlling Automatic Movements in Animals',Progress in Neurobiology 39,pp.45-112.Google Scholar
  3. Barto, A.G., Sutton, R.S.and Anderson, C.W.(1983),'Neuronlike Adaptive Elements that Can Solve Di.cult Learning Control Problems', IEEE Transactions on Systems,Man,and Cybernetics,SMX-13,pp.834-846.Google Scholar
  4. Bates, E.A.and Elman, J.L.(1996),'Learning Rediscovered, Science 274,pp.1849-1850.Google Scholar
  5. Bell, J.S.(1966),'On the Problem of Hidden Variables in Quantum Mechanics',Reviews of Modern Physics 38,pp.447-452.Google Scholar
  6. Bertsekas, D.P.(2000),Dynamic Programming and Optimal Control,Belmont: Athena Scientific.Google Scholar
  7. Bertsekas, D.P.and Tsitsiklis, J.N.(1996),Neuro-Dynamic Programming,Belmont: Athena Scientific.Google Scholar
  8. Bhushan, N.and Shadmehr,R.(1999),'Computational Nature of Human Adaptive Control During Learning of Reaching Movements in Force Fields',Biological Cybernetics 81,pp.39-60.Google Scholar
  9. Calvin, W.H.and Bickerton,D.(2000),Lingua ex machina:Reconciling Darwin and Chomsky with the Human Brain,Cambridge,MA: MIT Press.Google Scholar
  10. Chomsky,N.(1966),Topics in the Theory of Generative Grammar,The Hague: Mouton.Google Scholar
  11. Chomsky,N.(1980),'On Cognitive Structures and Their Development:A Reply to Piaget',in M.Piatelli-Palmarini,ed.,Language and Learning,Cambridge,MA: Harvard University Press,pp.35-52.Google Scholar
  12. Cutland,N.(1980),Computability,Cambridge: Cambridge University Press.Google Scholar
  13. Cziko,G.(1995),Without Miracles.Universal Selection Theory and the Second Darwinian Revolution,Cambridge,MA: MIT Press.Google Scholar
  14. Elman, J.L., Bates, E.A., Hohnson, M.H., Karmilo.-Smith, A., Parisi, D. and Plunkett,K. (1996),Rethinking Innateness,Cambridge,MA: MIT Press.Google Scholar
  15. Fodor, J.(1980),'Fixation of Belief and Concept Acquisition ',in M.Piatelli-Palmarini,ed., Language Learning Cambridge,MA: Harvard University Press,pp.143-149.Google Scholar
  16. Gerdes, V.G.and Happee,R.(1994),'The Use of Internal Representation in Fast Gold-Directed Movements:A Modeling Approach ',Biological Cybernetics 70,pp.513-524.Google Scholar
  17. Gold,E.(1967),'Language Identification in the Limit ',Information and Control 10,pp.447-474.Google Scholar
  18. Hebb, D.O.(1949),The Organization of Behavior,New York: Wiley.Google Scholar
  19. Hutter, M.(2001),'Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions ',in D.L. Raedt and P. Flash,eds.,Proceedings of the 12th European Conference of Machine Learning,Berlin: Springer-Verlag,pp. 226-238.Google Scholar
  20. Johansson, R.and Magnusson,M.(1991),'Optimal Coordination and Control of Posture and Locomotion ',Mathematical Biosciences 103,pp.203-244.Google Scholar
  21. Kieu, T.D.(2003),'Quantum Algorithm for Hilbert 's Tenth Problem',International Journal Theoretical Physics 42,pp.1461-1478.Google Scholar
  22. Kirkpatrick,S., Gelatt, C.D.and Vecchi, M.P.(1983),'Optimization by Simulated Annealing ',Science 228,pp.671-680.Google Scholar
  23. Lan, N.(1997),'Analysis of an Optimal Control Model of Multi-Joint Arm Movements ', Biological Cybernetics 76,pp.107-117.Google Scholar
  24. Langley, P.(1996),Elements of Machine Learning,San Francisco: Morgan Kaufmann.Google Scholar
  25. Lawrie, I.D.(1990),A Unified Grand Tour of Theoretical Physics,Bristol: Institute of Physics Publishing.Google Scholar
  26. Leeuw, K.D., Moore, E.F., Shannon, C.E.and Shapiro,N.(1956),'Computability by Probabilistic Machines',in C.E. Shannon and J. McCarthy,eds.,Automata Studies, Princeton: Princeton University Press,pp.183-212.Google Scholar
  27. Li, M.and Vitanyi, P.M.B.(1997),An Introduction to Kolmogorov Complexity and its Applications,Berlin: Springer.Google Scholar
  28. Mayr,E.(1982),'Teleological and Teleonomical:A New Analysis',in H.C. Plotkin,ed., Learning,Development,and Culture,New York: Wiley.Google Scholar
  29. McCulloch, W.S.and Pitts, W.H.(1943),'A Logical Calculus of the Idea Immanent in Nervous Activity ',Bulletin Mathematical Biophysics 5,pp.115-133.Google Scholar
  30. Mitchell, M.(1996),An Introduction to Genetic Algorithms,Cambridge, MA:MIT Press.Google Scholar
  31. Penrose, R.(1994),Shadows of the Mind,New York: Oxford University Press.Google Scholar
  32. Piaget, J.(1972),The Principles of Genetic Epistemology,New York: Basic Books.Google Scholar
  33. Piaget, J.(1980),'The Psychogenesis of Knowledge and its Epistemological Significance',in M. Piatelli-Palmarini,ed.,Language and Learning,Cambridge,MA: Harvard University Press,pp.23-34.Google Scholar
  34. Piatelli-Palmarini, M.(1989),'Evolution,Selection and Cognition:From ''Learning ''to Parameter Setting in Biology and the Study of Language ',Cognition 31,pp.1-44.Google Scholar
  35. Pla-Lopez, R.(1988),'Introduction to a Learning General Theory ',Cybernetics and Systems: An International Journal 19,pp.411-429.Google Scholar
  36. Pontryagin, L.S., Boltyanskii, V.G., Gamkrelidze, R.V.and Mishchenko, E.F.(1962),The Mathematical Theory of Optimal Processes,New York: Interscience.Google Scholar
  37. Rosenblatt,F.(1962),Principles of Neurodynamics,New York: Spartan Books.Google Scholar
  38. Rumelhart, D.E., Hinton, G.E.and Williams, R.J.(1986),'Learning Representations by Back-Propagating Errors ',Nature 323,pp.533-536.Google Scholar
  39. Shimansky, Y.P.(2000),'Spinal Motor Control System Incorporates an Internal Model of Limb Dynamics ',Biological Cybernetics 83,pp.379-389.Google Scholar
  40. Shimansky, Y.P., Kang, T.and He,J.(2004),'A Novel Model of Motor Learning Capable of Developing an Optimal Movement Trajectory On-Line from Scratch ',Biological Cyber-netic s 90,pp.133-145.Google Scholar
  41. Shoucri, R.M.(1991),'Pump Function of the Heart as an Optimal Control Problem ',Journal of Biomedical Engineering 13,pp.384-390.Google Scholar
  42. Solomono., R.J.(1964),'A Formal Theory of Inductive Inference',Information and Control 7, pp.1-2.Google Scholar
  43. Sutton, R.S.and Barto, A.G.(1998),Reinforcement Learning:An Introduction,Cambridge, MA: MIT Press.Google Scholar
  44. Uspensky, V.and Semenov,A.(1993),Algorithms:Main Ideas and Applications,Dordrecht: Kluwer Academic Publishers.Google Scholar
  45. Wolpert, D.M., Ghahramani, Z.and Jordan, M.I.(1995),'An Internal Model for Sensori-motor Integration',Science 269,pp.1880-1882.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Yury P. Shimansky
    • 1
  1. 1.Harrington Department of Bioengineering, Center for Neural Interface Design, Arizona Biodesign InstituteArizona State UniversityTempeUSA

Personalised recommendations