Advertisement

Neural Computations That Support Long Mixed Sequences of Knowledge Acquisition Tasks

  • Leslie G. Valiant
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5532)

Abstract

In this talk we shall first give a brief review of a quantitative approach to understanding neural computation [4-6]. We target so-called random access tasks, defined as those in which one instance of a task execution may need to access arbitrary combinations of items in memory. Such tasks are communication intensive, and therefore the known severe constraints on connectivity in the brain can inform their analysis.

References

  1. [1]
    Hoory, S., Linial, N., Wigderson, A.: Expander graphs and their applications. Bull. Amer. Math. Soc. 43, 439–561 (2006)zbMATHCrossRefMathSciNetGoogle Scholar
  2. [2]
    Graham, B., Willshaw, D.: Capacity and information efficiency of the associative net. Network: Comput. Neural Syst. 8, 35–54 (1997)zbMATHCrossRefGoogle Scholar
  3. [3]
    Feldman, V., Valiant, L.G.: Experience-induced neural circuits that achieve high capacity. Neural Computation (to appear, 2009)Google Scholar
  4. [4]
    Valiant, L.G.: Circuits of the Mind. Oxford University Press, Oxford (1994, 2000)Google Scholar
  5. [5]
    Valiant, L.G.: Memorization and association on a realistic neural model. Neural Computation 17(3), 527–555 (2005)zbMATHCrossRefGoogle Scholar
  6. [6]
    Valiant, L.G.: A quantitative theory of neural computation. Biological Cybernetics 95(3), 205–211 (2006)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Leslie G. Valiant
    • 1
  1. 1.School of Engineering and Applied SciencesHarvard University 

Personalised recommendations