This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: | This paper investigates potential learning rules in the cerebellum. We review evidence that input to the cerebellum is sparsely expanded by granule cells into a very wide basis vector, and that Purkinje cells learn to compute a linear separation using that basis. We review learning rules employed by existing cerebellar models, and show that recent results from Computational Learning Theory suggest that the standard delta rule would not be efficient. We suggest that alternative, attribute-efficient learning rules, such as Winnow or Incremental Delta-Bar-Delta, are more appropriate for cerebellar modeling, and support this position with results from a computational model. altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: July 2001 conference: International Joint Conference on Neural Networks 2001 confloc: 'Washington, DC, USA' contact_email: ~ creators_id: [] creators_name: - family: Harris given: Harlan honourific: '' lineage: '' - family: Reichler given: Jesse honourific: '' lineage: '' date: 2001 date_type: published datestamp: 2002-07-03 department: ~ dir: disk0/00/00/23/10 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Marko given: Kenneth honourific: '' lineage: '' - family: Werbos given: Paul honourific: '' lineage: '' eprint_status: archive eprintid: 2310 fileinfo: /style/images/fileicons/application_postscript.png;/2310/2/sparsewinnow.ps full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: 'cerebellum, modeling, learning theory, winnow, idbd' lastmod: 2011-03-11 08:54:57 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: ~ pubdom: FALSE publication: ~ publisher: IEEE refereed: TRUE referencetext: |+ David Marr. A theory of cerebellar cortex. Journal of Physiology, 202:437--470, 1969. J. S. Albus. The theory of cerebellar function. Mathematical Bioscience, 10:25--61, 1971. James C. Houk, Jay T. Buckingham, and Andrew G. Barto. Models of the cerebellum and motor learning. Behavioral and Brain Sciences, 19:368--383, 1996. J. L. Krichmar, G. A. Ascoli, L. Hunter, and J. L. Olds. A mode lof cerebellar saccadic motor learning using qualitative reasoning. Lecture Notes in Computer Science, Artificial and Natural Neural Networks, 1240:134--145, 1997. James C. Houk and Andres G. Barto. Distributed sensorimotor learning. In G. E. Stelmach and J. Requin, editors, Tutorials in Motor Behavior II, pages 71--100. Elsevier Science Publishers B. V., Amsterdam, The Netherlands, 1992. Young H. Kim and Frank L. Lewis. Optimal design of CMAC neural-network controller for robot manipulators. IEEE Transactions on Systems, Man, and Cybernetics Part C: Applications and Reviews, 30(1), 2000. Toby Tyrrell and David Willshaw. Cerebellar cortex: its simulation and the relevance of marr's theory. Philosophical Transactions of the Royal Society of London, B, 336:239--257, 1992. Nick Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285--318, 1988. J. Kivinen, M. K. Warmuth, and P. Auer. The Perceptron algorithm versus Winnow: Linear versus logarithmic mistake bounds when few input variables are relevant. Artificial Intelligence, 97:325--343, 1997. Richard S. Sutton. Adapting bias by gradient descent: An incremental version of Delta-Bar-Delta. In Proceedings of the Tenth National Conference on Artificial Intelligence, pages 171--176. MIT Press, 1992. Robert A. Jacobs. Increased rates of convergence through learning rate adaptation. Neural Networks, 1:295--307, 1988. Nicolas Schweighofer and Michael A. Arbib. A model of cerebellar metaplasticity. Learning and Memory, 4:421--428, 1998. Valentino Braitenberg, Deflek Heck, and Fehad Sultan. The detection and generation of sequences as a key to cerebellar function: Experiments and theory. Behavioral and Brain Sciences, 20:229--277, 1997. T. M. Cover. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Transactions on Electronic Computers, EC-14:326--334, 1965. J. S. Albus. A new approach to manipulator control: The cerebellar model articulation controller (CMAC). Trans. ASME J. Dynamic Systems, Measurement, and Control, 97:220--227, 1975. Jyrki Kivinen and Manfred K. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132(1):1--63, 10 January 1997. Andrew R. Golding and Dan Roth. A Winnow based approach to context-sensitive spelling correction. Machine Learning, 34:107--130, 1999. Claudio Gentile and Nick Littlestone. The robustness of the p-norm algorithms. In COLT 1999, 1999. relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:44:07 subjects: - comp-neuro-sci - neuro-mod succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Learning in the Cerebellum with Sparse Conjunctions and Linear Separator Algorithms type: confpaper userid: 3218 volume: ~