Advertisement

Fast and Slow Learning in a Neuro-Computational Model of Category Acquisition

Conference paper
First Online:
  • 2.3k Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9886)

Abstract

We present a neuro-computational model that, based on brain principles, succeeds in performing a category learning task. In particular, the network includes a fast learner (the basal ganglia) that via reinforcement learns to execute the task, and a slow learner (the prefrontal cortex) that can acquire abstract representations from the accumulation of experiences and ultimately pushes the task level performance to higher levels.

Keywords

Categorization Basal ganglia Fast-learner Reinforcement learning Prefrontal cortex Slow-learner 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

This work has been funded by DFG HA2630/4-1 and in part by DFG HA2630/8-1.

References

  1. 1.
    Poldrack, R.A., Prabhakaran, V., Seger, C.A., Gabrieli, J.D.E.: Striatal activation during acquisition of a cognitive skill. Neuropsychology 13, 564 (1999)CrossRefGoogle Scholar
  2. 2.
    Poldrack, R.A., Clark, J., Pare-Blagoev, E.J., Shohamy, D., Moyano, J.C., Myers, C., Gluck, M.A.: Interactive memory systems in the human brain. Nature 414, 546–550 (2001)CrossRefGoogle Scholar
  3. 3.
    Nomura, E., Maddox, W.T., Filoteo, J.V., Ing, A.D., Gitelman, D.R., Parrish, T.B., Mesulam, M.M., Reber, P.J.: Neural correlates of rule-based and information-integration visual category learning. Cere. Cortex 17, 37–43 (2007)CrossRefGoogle Scholar
  4. 4.
    Seger, C.A., Cincotta, C.M.: The roles of the caudate nucleus in human classification learning. J. Neurosci. 11, 2941–2951 (2005)CrossRefGoogle Scholar
  5. 5.
    Zeithamova, D., Maddox, W.T., Schnyer, D.M.: Dissociable prototype learning systems: evidence from brain imaging and behavior. J. Neurosci. 28, 13194–13201 (2008)CrossRefGoogle Scholar
  6. 6.
    Merchant, H., Zainos, A., Hernández, A., Salinas, E., Romo, R.: Functional properties of primate putamen neurons during the categorization of tactile stimuli. J. Neurophysiol. 77, 1132–1154 (1997)Google Scholar
  7. 7.
    Cincotta, C.M., Seger, C.A.: Dissociation between striatal regions while learning to categorize via feedback and via observation. J. Cognit. Neurosci. 19, 249–265 (2007)CrossRefGoogle Scholar
  8. 8.
    Humphries, M.D., Stewart, R.D., Gurney, K.N.: A physiologically plausible model of action selection and oscillatory activity in the basal ganglia. J. Neurosci. 26, 12921–12942 (2006)CrossRefGoogle Scholar
  9. 9.
    Grillner, S., Hellgren, J., Menard, A., Saitoh, K., Wikström, M.A.: Mechanisms for selection of basic motor programs-roles for the striatum and pallidum. Trends Neurosci. 28, 364–370 (2005)CrossRefGoogle Scholar
  10. 10.
    Hélie, S., Ell, S.W., Ashby, F.G.: Learning robust cortico-cortical associations with the basal ganglia: an integrative review. Cortex 64, 123–135 (2015)CrossRefGoogle Scholar
  11. 11.
    Freedman, D.J., Riesenhuber, M., Poggio, T., Miller, E.K.: A comparison of primate prefrontal and inferior temporal cortices during visual categorization. J. Neurosci. 23, 5235–5246 (2003)Google Scholar
  12. 12.
    Freedman, D.J., Riesenhuber, M., Poggio, T., Miller, E.K.: Visual categorization and the primate prefrontal cortex: neurophysiology and behavior. J. Neurophysiol. 88, 929–941 (2002)Google Scholar
  13. 13.
    Freedman, D.J., Riesenhuber, M., Poggio, T., Miller, E.K.: Categorical representation of visual stimuli in the primate prefrontal cortex. Science 291, 312–316 (2001)CrossRefGoogle Scholar
  14. 14.
    Miller, E.K., Cohen, J.D.: An integrative theory of prefrontal cortex function. Ann. Rev. Neurosci. 24, 167–202 (2001)CrossRefGoogle Scholar
  15. 15.
    Vitay, J., Dinkelbach, H., Hamker, F.H.: ANNarchy: a code generation approach to neural simulations on parallel hardware. Front. Neuroinf. 9, 19 (2015)CrossRefGoogle Scholar
  16. 16.
    Schroll, H., Vitay, J., Hamker, F.H.: Dysfunctional and compensatory synaptic plasticity in Parkinson’s disease. Eur. J. Neurosci. 39, 688–702 (2014)CrossRefGoogle Scholar
  17. 17.
    Baladron, J., Hamker, F.H.: A spiking neural network based on the basal ganglia functional anatomy. Neural Netw. 67, 1–13 (2015)CrossRefGoogle Scholar
  18. 18.
    Packard, M.G., Knowlton, B.J.: Learning and memory functions of the basal ganglia. Ann. Rev. Neurosci. 25, 563–593 (2002)CrossRefGoogle Scholar
  19. 19.
    Seger, C.A., Miller, E.K.: Category learning in the brain. Ann. Rev. Neurosci. 33, 203 (2010)CrossRefGoogle Scholar
  20. 20.
    Antzoulatos, E.G., Miller, E.K.: Differences between neural activity in prefrontal cortex and striatum during learning of novel abstract categories. Neuron 71, 243–249 (2011)CrossRefGoogle Scholar
  21. 21.
    Miller, E.K., Buschman, T.J.: Rules through recursion: how interactions between the frontal cortex and basal ganglia may build abstract, complex rules from concrete, simple ones. In: Neuroscience of Rule-Guided Behavior, pp. 419–440 (2007)Google Scholar
  22. 22.
    Seger, C.A.: The basal ganglia in human learning. Neuroscientist 12, 285–290 (2006)CrossRefGoogle Scholar
  23. 23.
    Haber, S.N.: The primate basal ganglia: parallel and integrative networks. J. Chem. Neuroanat. 26, 317–330 (2003)CrossRefGoogle Scholar
  24. 24.
    McHaffie, J.G., Stanford, T.R., Stein, B.E., Coizet, V., Redgrave, P.: Subcortical loops through the basal ganglia. Trends Neurosci. 28, 401–407 (2005)CrossRefGoogle Scholar
  25. 25.
    Stallkamp, J., Schlipsing, M., Salmen, F., Igel, C.: Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw. 32, 323–332 (2012)CrossRefGoogle Scholar
  26. 26.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)CrossRefGoogle Scholar
  27. 27.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (1998)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Artificial IntelligenceChemnitz University of TechnologyChemnitzGermany

Personalised recommendations

Cite paper

Buy options