Unsupervised Learning of Relations

  • Matthew Cook
  • Florian Jug
  • Christoph Krautz
  • Angelika Steger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6352)

Abstract

Learning processes allow the central nervous system to learn relationships between stimuli. Even stimuli from different modalities can easily be associated, and these associations can include the learning of mappings between observable parameters of the stimuli. The data structures and processing methods of the brain, however, remain very poorly understood. We investigate the ability of simple, biologically plausible processing mechanisms to learn such relationships when the data is represented using population codes, a coding scheme that has been found in a variety of cortical areas. We require that the relationships are learned not just from the point of view of an omniscient observer, but rather the network itself must be able to make effective use of the learned relationship, within the population code representations. Using a form of Hebbian learning, local winner-take-all, and homeostatic activity regulation away from the periphery, we obtain a learning framework which is able to learn relationships from examples and then use the learned relationships for a variety of routine nervous system tasks such as inference, de-noising, cue-integration, and decision making.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Carew, T.J., Hawkins, R.D., Kandel, E.: Differential classical conditioning of a defensive withdrawal reflex in aplysia californica. Science 219(4583), 397–400 (1983)CrossRefGoogle Scholar
  2. 2.
    Pavlov, I.: Conditioned Reflexes: An Investigation of the Physiological Activity of the Cerebral Cortex. Oxford University Press, London (1927)Google Scholar
  3. 3.
    Rescorla, R., Wagner, A.: Variations in the Effectiveness of Reinforcement and Nonreinforcement. In: Classical Conditioning II: Current Research and Theory, pp. 64–99. Appleton-Century-Crofts, New York (1972)Google Scholar
  4. 4.
    Wagner, A.R., Logan, F.A., Haberlandt, K., Price, T.: Stimulus selection in animal discrimination learning. J. Exp. Psychol. 76(2), 171–180 (1968)CrossRefGoogle Scholar
  5. 5.
    Bailey, C., Kandel, E.: Structural changes accompanying memory storage. Annu. Rev. Physiol. 55, 397–426 (1993)CrossRefGoogle Scholar
  6. 6.
    Bailey, C., Chen, M.: Morphological basis of long-term habituation and sensitization in aplysia. Science 220(4592), 91–93 (1983)CrossRefGoogle Scholar
  7. 7.
    Bailey, C., Chen, M.: Morphological basis of short-term habituation in aplysia. J. Neurosci. 8(7), 2452–2459 (1988)Google Scholar
  8. 8.
    Kandel, E., Spencer, W.A.: Electrophysiology of hippocampal neurons. ii. after-potentials and repetitive firing. J. Neurophysiol. 24, 243–259 (1961)Google Scholar
  9. 9.
    Salinas, E., Sejnowski, T.: Gain modulation in the central nervous system: where behavior, neurophysiology, and computation meet. Neuroscientist, 430–440 (2001)Google Scholar
  10. 10.
    Rutishauser, U., Ross, I., Mamelak, A., Schuman, E.: Human memory strength is predicted by theta-frequency phase-locking of single neurons. Nature (2010) (online first)Google Scholar
  11. 11.
    Barco, A., Bailey, C.H., Kandel, E.: Common molecular mechanisms in explicit and implicit memory. J. Neurochem. 97(6), 1520–1533 (2006)CrossRefGoogle Scholar
  12. 12.
    Kandel, E.: Cellular mechanisms of learning and the biological basis of individuality. In: Principles of Neural Science, 4th edn., McGraw-Hill, New York (1991)Google Scholar
  13. 13.
    Martin, S.J., Grimwood, P.D., Morris, R.G.: Synaptic plasticity and memory: an evaluation of the hypothesis. Annu. Rev. Neurosci. 23, 649–711 (2000)CrossRefGoogle Scholar
  14. 14.
    Felleman, D., Essen, D.V.: Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1(1), 1–47 (1991)CrossRefGoogle Scholar
  15. 15.
    Salinas, E., Abbott, L.F.: Coordinate transformations in the visual system: how to generate gain fields and what to compute with them. Prog. Brain Res. 130, 175–190 (2001)CrossRefGoogle Scholar
  16. 16.
    Pouget, A., Sejnowski, T.: Spatial transformations in the parietal cortex using basis functions. J. Cognitive Neurosci. 9(2), 222–237 (1997)CrossRefGoogle Scholar
  17. 17.
    Zipser, D., Andersen, R.A.: A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature 331(6158), 679–684 (1988)CrossRefGoogle Scholar
  18. 18.
    Rumelhart, D.E., Hinton, G., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  19. 19.
    Crick, F.: The recent excitement about neural networks. Nature 337, 129–132 (1989)CrossRefGoogle Scholar
  20. 20.
    Zipser, D., Rumelhart, D.: The neurobiological significance of the new learning models. In: Computational Neuroscience. MIT Press, Cambridge (1993)Google Scholar
  21. 21.
    Deneve, S., Latham, P., Pouget, A.: Efficient computation and cue integration with noisy population codes. Nat. Neurosci. 4(8), 826–831 (2001)CrossRefGoogle Scholar
  22. 22.
    Douglas, R., Martin, K.: Recurrent neuronal circuits in the neocortex. Curr. Biol. 17(13), 496–500 (2007)CrossRefGoogle Scholar
  23. 23.
    Hebb, D.: The Organization of Behavior: A Neuropsychological Theory. Wiley, New York (1949)Google Scholar
  24. 24.
    Turrigiano, G., Nelson, S.: Homeostatic plasticity in the developing nervous system. Nat. Rev. Neurosci. 5, 97–107 (2004)CrossRefGoogle Scholar
  25. 25.
    Georgopoulos, A.P., Kalaska, J.F., Caminiti, R., Massey, J.T.: On the relations between the direction of two-dimensional arm movements and cell discharge in primate motor cortex. J. Neurosci. 2(11), 1527–1537 (1982)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Matthew Cook
    • 1
  • Florian Jug
    • 2
  • Christoph Krautz
    • 2
  • Angelika Steger
    • 2
  1. 1.Institute of NeuroinformaticsUniversity of Zurich and ETH ZurichSwitzerland
  2. 2.Institute of Theoretical Computer ScienceETH ZurichSwitzerland

Personalised recommendations