Post and pre-compensatory Hebbian learning for categorisation

Abstract

A system with some degree of biological plausibility is developed to categorise items from a widely used machine learning benchmark. The system uses fatiguing leaky integrate and fire neurons, a relatively coarse point model that roughly duplicates biological spiking properties; this allows spontaneous firing based on hypo-fatigue so that neurons not directly stimulated by the environment may be included in the circuit. A novel compensatory Hebbian learning algorithm is used that considers the total synaptic weight coming into a neuron. The network is unsupervised and entirely self-organising. This is relatively effective as a machine learning algorithm, categorising with just neurons, and the performance is comparable with a Kohonen map. However the learning algorithm is not stable, and behaviour decays as length of training increases. Variables including learning rate, inhibition and topology are explored leading to stable systems driven by the environment. The model is thus a reasonable next step toward a full neural memory model.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Notes

  1. 1.

    This elevated firing in the internal subnets contrasts with the firing in those nets when inhibition is added. Figure 5c, d reflect the firing behaviour when extra inhibition is added (see “Homeostasis” section).

  2. 2.

    It should be noted that the three input task is different, and naturally performance will be lower as there is less input. Performance on the full twofold task at 20,000 cycles with 100 nets measuring by firing is 79.65 %.

References

  1. Abbott L (1999) Lapicque’s introduction of the integrate-and-fire model neuron (1907). Brain Res 50:303–304

    CAS  Google Scholar 

  2. Ackley D, Hinton G, Sejnowski T (1985) A learning algorithm for Boltzmann machines. Cogn Sci 9:147–169

    Article  Google Scholar 

  3. Amit D (1989) Modelling brain function: the world of attractor neural networks. Cambridge University Press, Cambridge

    Book  Google Scholar 

  4. Athitsos V, Sclaroff S (2004) Boosting nearest neighbor classifiers for multiclass recognition. Technical report, Boston University

  5. Bache K, Lichman M (2013) UCI machine learning repository. School of Information and Computer Science, University of California, Irvine. http://archive.ics.uci.edu/ml

  6. Bi G, Poo M (1998) Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. J Neurosci 18:24:10464–10472

    Google Scholar 

  7. Bienenstock E, Cooper L, Munro P (1982) Theory for the development of neuron selectivity: orientation specificity and binocular interaction in the visual cortex. J Neurosci 2:1:32–48

    Google Scholar 

  8. Brette R, Rudolph M, Carnevale T, Hines M, Beeman D, Bower J, Diesmann M, Morrison A, Goodman P, Harris F, Zirpe M, Natschalager T, Pecevski D, Ermentrout B, Djurfeldt M, Lansner A, Rochel O, Vieville T, Muller E, Dafison A, ElBoustani S, Destexhe A (2007) Simulation of networks of spiking neurons: a review of tools and strategies. J Comput Neurosci 23:349–398

    PubMed Central  PubMed  Article  Google Scholar 

  9. Bush D, Philippides A, Husbands P, O’Shea M (2010) Reconciling the stdp and bcm models of synaptic plasticity in a spiking recurrent neural network. Neural Comput 22:2059–2085

    PubMed  Article  Google Scholar 

  10. Freedman D, Riesenhuber M, Poggio T, Miller E (2001) Categorical representation of visual stimuli in the primate prefrontal cortex. Science 291:312–316

    CAS  PubMed  Article  Google Scholar 

  11. Fyfe C (2005) Hebbian learning and negative feedback networks. Springer, Berlin

    Google Scholar 

  12. Hebb D (1949) The organization of behavior. Wiley, London

    Google Scholar 

  13. Hodgkin A, Huxley A (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117:500–544

    CAS  PubMed Central  PubMed  Google Scholar 

  14. Hsu D, Tan A, Hsu M, Beggs J (2007) A simple spontaneously active hebbian learning model: homeostasis of activity and connectivity, and consequences for learning and epileptogensis. Phys Rev E 76:041909

    Article  Google Scholar 

  15. Huyck C (2007) Creating hierarchical categories using cell assemblies. Connect Sci 19:1:1–24

    Article  Google Scholar 

  16. Huyck C, Mitchell I (2013) Compensatory hebbian learning for categorisation in simulated biological neural nets. Biol Inspir Cogn Arch 6:3–7

    Google Scholar 

  17. Huyck C, Orengo V (2005) Information retrieval and categorisation using a cell assembly network. Neural Comput Appl 14:282–289

    Article  Google Scholar 

  18. Huyck C, Parvizi A (2012) Parameter values and fatigue mechanisms for flif neurons. J Syst Cybern Inf 10:4:80–86

    Google Scholar 

  19. Izhikevich E (2004) Which model to use for cortical spiking neurons? IEEE Trans Neural Netw 15:5:1063–1070

    Article  Google Scholar 

  20. Izhikevich E, Desai N (2003) Relating stdp to bcm. Neural Comput 15:1511–1523

    PubMed  Article  Google Scholar 

  21. Kohn A (2007) Visual adaptation: Physiology, mechanisms, and functional benefits. J Neurophysiol 97:3155–3164

    PubMed  Article  Google Scholar 

  22. Kohonen T (1997) Self-organizing maps. Springer, London

    Book  Google Scholar 

  23. McCulloch W, Pitts W (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys 5:115–133

    Article  Google Scholar 

  24. Mitchell I, Huyck C (2013) Self organising maps with a point neuron model. In 17th international conference on cognitive and neural systems

  25. O’Reilly R (1996) The Leabra Model of Neural Interactions and Learning in the Neocortex. PhD thesis, Carnegie Mellon University, Pittsburgh, PA

  26. Wehrens R, Buydens L (2007) Self- and super-organizing maps in R: the Kohonen package. J Stat Softw 21(5):1–9

    Google Scholar 

  27. Wolpert D, Macready W (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1:67–82

    Article  Google Scholar 

  28. Wu Q, Maguire L, Glackin B, Belatreche A (2006) Learning under weight constraints in networks of temporal encoding spiking neurons. Neurocomputing 69:1912–1922

    Article  Google Scholar 

Download references

Acknowledgments

Thanks to Zhijun Yang and Dan Diaper for comments on this paper.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Christian R. Huyck.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Huyck, C.R., Mitchell, I.G. Post and pre-compensatory Hebbian learning for categorisation. Cogn Neurodyn 8, 299–311 (2014). https://doi.org/10.1007/s11571-014-9282-4

Download citation

Keywords

  • Compensatory Hebbian learning
  • Categorisation
  • Spontaneous neural spiking
  • Neural fatigue
  • Point neural model
  • Self-organisation