Biological Cybernetics

, Volume 94, Issue 2, pp 128–142 | Cite as

Learning invariant object recognition in the visual system with continuous transformations

  • S. M. Stringer
  • G. Perry
  • E. T. Rolls
  • J. H. Proske
Original Paper

Abstract

The cerebral cortex utilizes spatiotemporal continuity in the world to help build invariant representations. In vision, these might be representations of objects. The temporal continuity typical of objects has been used in an associative learning rule with a short-term memory trace to help build invariant object representations. In this paper, we show that spatial continuity can also provide a basis for helping a system to self-organize invariant representations. We introduce a new learning paradigm “continuous transformation learning” which operates by mapping spatially similar input patterns to the same postsynaptic neurons in a competitive learning system. As the inputs move through the space of possible continuous transforms (e.g. translation, rotation, etc.), the active synapses are modified onto the set of postsynaptic neurons. Because other transforms of the same stimulus overlap with previously learned exemplars, a common set of postsynaptic neurons is activated by the new transforms, and learning of the new active inputs onto the same postsynaptic neurons is facilitated. We demonstrate that a hierarchical model of cortical processing in the ventral visual system can be trained with continuous transform learning, and highlight differences in the learning of invariant representations to those achieved by trace learning.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Almassy N, Edelman GM, Sporns O (1998) Behavioral constraints in the development of neuronal properties: a cortical model embedded in a real-world device. Cereb Cortex 8:346–361PubMedCrossRefGoogle Scholar
  2. Artola A, Singer W (1993) Long-term depression of excitatory synaptic transmission and its relationship to long-term potentiation. Trends Neurosci 16:480–487PubMedCrossRefGoogle Scholar
  3. Bartlett MS, Sejnowski TJ (1998) Learning viewpoint-invariant face representations from visual experience in an attractor network. Netw Comput Neural Syst 9:399–417CrossRefGoogle Scholar
  4. Becker S (1999) Implicit learning in 3D object recognition: the importance of temporal context. Neural Comput 11:347–374PubMedCrossRefGoogle Scholar
  5. Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev 94:115–147PubMedCrossRefGoogle Scholar
  6. Booth MCA, Rolls ET (1998) View-invariant representations of familiar objects by neurons in the inferior temporal visual cortex. Cerebral Cortex 8:510–523PubMedCrossRefGoogle Scholar
  7. Desimone R (1991) Face-selective cells in the temporal cortex of monkeys. J Cognit Neurosci 3:1–8Google Scholar
  8. Elliffe MCM, Rolls ET, Stringer SM (2002) Invariant recognition of feature combinations in the visual system. Biol Cybern 86:59–71PubMedCrossRefGoogle Scholar
  9. Földiák P (1991) Learning invariance from transformation sequences. Neural Comput 3:194–200Google Scholar
  10. Frégnac Y (1996) Dynamics of cortical connectivity in visual cortical networks: an overview. J Physiol Paris 90:113–139PubMedCrossRefGoogle Scholar
  11. Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36:193–202PubMedCrossRefGoogle Scholar
  12. Fukushima K (2003) Neocognitron for handwritten digit recognition. Neurocomputing 51:161–180CrossRefGoogle Scholar
  13. Fukushima K, Tanigawa M (1996) Use of different thresholds in learning and recognition. Neurocomputing 11:1–17CrossRefGoogle Scholar
  14. Hasselmo ME, Rolls ET, Baylis GC, Nalwa V (1989) Object-centered encoding by face-selective neurons in the cortex in the superior temporal sulcus of the monkey. Exp Brain Res 75:417–429PubMedCrossRefGoogle Scholar
  15. Hertz J, Krogh A, Palmer RG (1991) Introduction to the theory of neural computation. Addison Wesley, Wokingham, UKGoogle Scholar
  16. Ito M, Tamura H, Fujita I, Tanaka K (1995) Size and position invariance of neuronal response in monkey inferotemporal cortex. J Neurophysiol 73:218–226PubMedGoogle Scholar
  17. Kobotake E, Tanaka K (1994). Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. J Neurophysiol 71:856–867Google Scholar
  18. Koenderink JJ (1990) Solid shape. MIT, CambridgeGoogle Scholar
  19. Op de Beeck H, Vogels R (2000) Spatial sensitivity of macaque inferior temporal neurons. J Comp Neurol 426:505–518CrossRefGoogle Scholar
  20. Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2:1019–1025PubMedCrossRefGoogle Scholar
  21. Rolls ET (1992) Neurophysiological mechanisms underlying face processing within and beyond the temporal cortical visual areas. Phil Trans Roy Soc 335:11–21CrossRefGoogle Scholar
  22. Rolls ET (2000) Functions of the primate temporal lobe cortical visual areas in invariant visual object and face recognition. Neuron 27:205–218PubMedCrossRefGoogle Scholar
  23. Rolls ET (2005) Emotion explained. Oxford University Press, OxfordGoogle Scholar
  24. Rolls ET, Baylis GC (1986) Size and contrast have only small effects on the responses to faces of neurons in the cortex of the superior temporal sulcus of the monkey. Exp Brain Res 65:38–48PubMedCrossRefGoogle Scholar
  25. Rolls ET, Cowey A (1970) Topography of the retina and striate cortex and its relationship to visual acuity in rhesus monkeys and squirrel monkeys. Exp Brain Res 10:298–310PubMedCrossRefGoogle Scholar
  26. Rolls ET, Baylis GC, Hasselmo ME (1987) The responses of neurons in the cortex in the superior temporal sulcus of the monkey to band-pass spatial frequency filtered faces. Vis Res 27:311–326PubMedCrossRefGoogle Scholar
  27. Rolls ET, Baylis GC, Leonard CM (1985) Role of low and high spatial frequencies in the face-selective responses of neurons in the cortex in the superior temporal sulcus. Vis Res 25:1021–1035PubMedCrossRefGoogle Scholar
  28. Rolls ET, Deco G (2002) Computational neuroscience of vision. Oxford University Press, OxfordGoogle Scholar
  29. Rolls ET, Milward T (2000) A model of invariant object recognition in the visual system: learning rules, activation functions, lateral inhibition, and information-based performance measures. Neural Comput 12:2547–2572PubMedCrossRefGoogle Scholar
  30. Rolls ET, Stringer SM (2001) Invariant object recognition in the visual system with error correction and temporal difference learning. Netw Comput Neural Syst 12:111–129CrossRefGoogle Scholar
  31. Rolls ET, Treves A, Tovee MJ (1997a) The representational capacity of the distributed encoding of information provided by populations of neurons in the primate temporal visual cortex. Exp Brain Res 114:149–162CrossRefGoogle Scholar
  32. Rolls ET, Treves A, Tovee M, Panzeri S (1997b) Information in the neuronal representation of individual stimuli in the primate temporal visual cortex. J Comput Neurosci 4:309–333CrossRefGoogle Scholar
  33. Singer W (1995) Development and plasticity of cortical processing architectures. Science 270:758–764PubMedCrossRefGoogle Scholar
  34. Stringer SM, Rolls ET (2002) Invariant object recognition in the visual system with novel views of 3D objects. Neural Comput 14:2585–2596PubMedCrossRefGoogle Scholar
  35. Tanaka K, Saito H, Fukada Y, Moriya M (1991) Coding visual images of objects in the inferotemporal cortex of the macaque monkey. JNeurophysiol 66:170–189Google Scholar
  36. Tovee MJ, Rolls ET, Azzopardi P (1994) Translation invariance and the responses of neurons in the temporal visual cortical areas of primates. J Neurophysiol 72:1049–1060PubMedGoogle Scholar
  37. Ullman S (1996) High-level vision. MIT, CambridgeGoogle Scholar
  38. Vogels R, Biederman I (2002) Effects of illumination intensity and direction on object coding in macaque inferior temporal cortex. Cereb Cortex 12:756–766PubMedCrossRefGoogle Scholar
  39. Wallis G, Rolls ET (1997) Invariant face and object recognition in the visual system. Progr Neurobiol 51:167–194CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  • S. M. Stringer
    • 1
  • G. Perry
    • 1
  • E. T. Rolls
    • 1
  • J. H. Proske
    • 1
  1. 1.Centre for Computational Neuroscience, Department of Experimental PsychologyOxford UniversityOxfordEngland

Personalised recommendations