Advertisement

Biological Cybernetics

, Volume 92, Issue 3, pp 192–198 | Cite as

Stochastic correlative firing for figure-ground segregation

  • Zhe Chen
Article

Abstract.

Segregation of sensory inputs into separate objects is a central aspect of perception and arises in all sensory modalities. The figure-ground segregation problem requires identifying an object of interest in a complex scene, in many cases given binaural auditory or binocular visual observations. The computations required for visual and auditory figure-ground segregation share many common features and can be cast within a unified framework. Sensory perception can be viewed as a problem of optimizing information transmission. Here we suggest a stochastic correlative firing mechanism and an associative learning rule for figure-ground segregation in several classic sensory perception tasks, including the cocktail party problem in binaural hearing, binocular fusion of stereo images, and Gestalt grouping in motion perception.

Keywords

Sensory Modality Associative Learning Learning Rule Sensory Perception Unify Framework 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Alonso, J-M, Usrey, WM, Reid, RC 1996Precisely correlated firing in cells of the lateral geniculate nucleusNature383815819Google Scholar
  2. Anstis, SM 1980The perception of apparent movementPhil Trans R Soc LondB290153168Google Scholar
  3. Arbib, M eds. 1995The handbook of brain theory and neural networksMIT PressCambridge, MAGoogle Scholar
  4. Atick, JJ 1992Can information theory provide an ecological theory of sensory processingNetwork3213251CrossRefGoogle Scholar
  5. Ballard, DH, Hinton, GE, Sejnowski, TJ 1983Parallel visual computationNature3062126Google Scholar
  6. Becker, S, Hinton, GE 1992A self-organizing neural network that discovers surfaces in random-dot stereogramsNature355161163Google Scholar
  7. Bell, AJ, Sejnowski, TJ 1995An information-maximization approach to blind separation and blind deconvolutionNeural Comput711291159Google Scholar
  8. Blais, BS, Intrator, N, Shouval, H, Cooper, LN 1998Receptive field formation in natural scene environments: comparison of single cell learning rulesNeural Comput1017971813Google Scholar
  9. Bregman, AS 1990Auditory scene analysisMIT PressCambridge, MAGoogle Scholar
  10. Brown, GD, Yamada, S, Sejnowski, TJ 2001Independent component analysis at the neural cocktail partyTrends Neurosci245463Google Scholar
  11. Chen Z, Haykin S (2004) Figure-ground segregation in sensory perception using a stochastic correlative learning rule. Technical Report, Adaptive Systems Lab, McMaster University, Hamilton, CanadaGoogle Scholar
  12. Cherry, EC 1953Some experiments on the recognition of speech, with one and two earsJ Acoust Soc Am25975979Google Scholar
  13. Cook, JE 1991Correlated activity in the CNS: a role on every timescale?Trends Neurosci14397401Google Scholar
  14. Eggermont, JJ 1990The correlative brainSpringerBerlin Heidelberg New YorkGoogle Scholar
  15. Field, DJ 1994What is the goal of sensory coding?Neural Comput6559601Google Scholar
  16. Geman, S, Geman, D 1984Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of imagesIEEE Trans Pattern Anal Mach Intell6721741zbMATHGoogle Scholar
  17. Grossberg, S, Mingolla, E 1985Neural dynamics of perceptual grouping: textures, boundaries and emergent segmentationsPercept Psychophys38141171Google Scholar
  18. Harth, E, Tzanakou, E 1974Alopex: a stochastic method for determining visual receptive fieldsVision Res1414751482Google Scholar
  19. Harth, E, Unnikrishnan, KP, Pandya, AS 1987The inversion of sensory processing by feedback pathways: a model of visual cognitive functionsScience237184187Google Scholar
  20. Haykin, S, Chen, Z, Becker, S 2004Stochastic correlative learning algorithmsIEEE Trans Signal Process5222002209Google Scholar
  21. Hebb, DO 1949The organization of behaviorWileyNew YorkGoogle Scholar
  22. Hyvärinen, A, Karhunen, J, Oja, E 2001Independent component analysisWileyNew YorkGoogle Scholar
  23. Julesz, B 1971Foundations of cyclopean perceptionUniversity of Chicago PressChicagoGoogle Scholar
  24. Kirkpatrick, S, Gelatt, CG, Vecchi, MP 1983Optimization by simulated annealingScience220671680MathSciNetGoogle Scholar
  25. König, P, Engel, AK 1995Correlated firing in sensory-motor systemsCurr Opin Neurobiol5511519Google Scholar
  26. Livingstone, M, Hubel, D 1988Segregation of form, color, movement, and depth: anatomy, physiology, and perceptionScience240740749Google Scholar
  27. Makeig, S, Jung, T-P, Bell, AJ, Ghahremani, D, Sejnowski, TJ 1997Blind separation of auditory event-related brain response into independent componentsProc Natl Acad Sci USA941097910984Google Scholar
  28. Marr, D, Poggio, T 1976Cooperative computation of stereo disparityScience194283287Google Scholar
  29. Marr, D, Poggio, T 1979A computational theory of human stereo visionProc R Soc Lond B204301328Google Scholar
  30. Miller, KD 1990Gluck, MARumelhart, DE eds. Neuroscience and connectionist theoryErlbaumHillsdale, NJ267353Google Scholar
  31. Olshausen, BA, Field, DJ 1996Emergence of simple-cell receptive field properties by learning a sparse code for natural imagesNature381607609Google Scholar
  32. Rao, RP 1999An optimal estimation approach to visual perception and learningVision Res3919631989Google Scholar
  33. Singer, W 1993Synchronization of cortical activity and its putative role in information processing and learningAnnu Rev Physiol55349374CrossRefPubMedGoogle Scholar
  34. Sporns, O, Tononi, G, Edelman, GM 1991Modeling perceptual grouping and figure-ground segregation by means of active reentrant connectionsProc Natl Acad Sci USA88129133Google Scholar
  35. Tzanakou, E 2000Supervised and unsupervised pattern recognitionCRC PressRoca Raton, FLGoogle Scholar
  36. Tzanakou, E, Michalak, R, Harth, E 1979The Alopex process: visual receptive fields by response feedbackBiol Cybern35161174Google Scholar
  37. Ullman, S 1979The interpretation of visual motionMIT PressCambridge, MAGoogle Scholar
  38. Unnikrishnan, KP, Venugopal, KP 1994Alopex: a correlation-based learning algorithm for feedforward and recurrent neural networksNeural Comput6469490Google Scholar
  39. Verri A, Straforini M, Torre V (1992) Computational aspects of motion perception in natural and artificial vision systems. Phil Trans R Soc Lond B pp 429–443Google Scholar
  40. Malsburg, C, Schneider, W 1986A neural cocktail-party processorBiol Cybern542940Google Scholar
  41. Malsburg, C 1999The what and why of binding: the modeler’s perspectiveNeuron2495104Google Scholar
  42. Yuille, AL, Grzywacz, NM 1988A computational theory for the perception of coherent visual motionNature3357174Google Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  1. 1.Adaptive Systems LabMcMaster UniversityHamiltonCanada

Personalised recommendations