A New Approach to Learning Via Self-Organization

  • Dimitris Stassinopoulos
  • Per Bak


Recently, we have introduced a simple “toy” brain model to address the problem of learning in the absence of external intelligence.1 Our model departs from the traditional gradient-descent based approaches to learning by operating at a highly susceptible “critical” state with low activity and sparse connections between firing neurons. Here, quantitative studies of the performance of our model in a simple association task show that tuning our system close to this critical state results in dramatic gains in performance.


Synaptic Weight Association Task Reinforcement Learning Model Input Site Output Site 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    D. Stassinopoulos and P. Bak, Phys. Rev. E 51, 5033 (1995).CrossRefGoogle Scholar
  2. [2]
    J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation ( Addison-Wesley, Redwood, 1991 ).Google Scholar
  3. [3]
    Based on the partial information provided by the critic a target pattern is determined and the output-weight errors computed. The rest of the weights can then be updated by back-propagating this error-signal through the network (see Hertz et al in Ref. 2).Google Scholar
  4. [4]
    A. G. Barto, Human Neurobiology 4, 229 (1985).PubMedGoogle Scholar
  5. [5]
    R. Alstrom and D. Stassinopoulos, Phys. Rev. E 51 5027 (1995).CrossRefGoogle Scholar
  6. [6]
    D. Stassinopoulos and P. Bak, in Proceedings of the Fourth Appalachian Conference on Behavioral Neurodynamics - Radford, edited by K. Pribram, ( Lawrence Erlbaum. New Jersey, 1996 ).Google Scholar
  7. [7]
    R. Bak, C. Tang. and K. Wiesenfeld, Phys. Rev. Lett. 59 381 (1987).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1997

Authors and Affiliations

  • Dimitris Stassinopoulos
    • 1
  • Per Bak
    • 2
  1. 1.Center for Complex SystemsFlorida Atlantic UniversityBoca RatonUSA
  2. 2.Department of PhysicsBrookhaven National LaboratoryUptonUSA

Personalised recommendations