Scope: This bibliography contains references of learning invariant representations in neural systems. It focusses on algorithms and does not include mainly application oriented papers.

Support level: Medium - 2002. This bibliography is medium well supported till the year 2002, i.e. I have collected quite a few references but the collection is not complete.

Publication types: All. This bibliography may also contain non-journal references, which are shown in grey and are not included in the bibtex file. Red titles indicate survey articles.

Online papers: An 'A' or 'P' (or 'T' for text only) after a reference link indicates that it leads to an abstract or full paper, respectively. Upper case letters refer to online documents provided by a journal, which might be accessible only to subscribers (indicated by a '?'). Lower case letters refer to online documents provided by an author. Also the links at the end of the references are differentiated in this way by upper and lower case letters at the beginning of the words 'abstract.html' etc. and by a '?', if the corresponding document is only accessible to subscribers. The site location is indicated by a preceding .uk, .com, etc.

BibTeX: A bibtex file for the journal article references is also available (compressed and uncompressed).

Feedback: Please feel free to send me any kind of feedback about this bibliography.

Related Resources

• Bibliography Invariances in Neural Systems (a superset of this bibliography)
• Bibliography Dynamic Link Matching
• Learning Shift Invariancy (email discussion on connectionists@cs.cmu.edu)

References

1. BarrBray92

Barrow, H.G. and Bray, A.J. (1992).
A Model of Adaptive Development of Complex Cortical Cells
In Artificial Neural Networks II: Proceedings of the International Conference on Artificial Neural Networks by Aleksander, I and Taylor, J. (eds.), Elsevier, Amsterdam, pp. 881-884..

2. BartSejn96a

Bartlett, M.S. and Sejnowski, T.J. (1996 a).
Unsupervised learning of invariant representations of faces through temporal association
In Computational Neuroscience: International Review of Neurobiology Suppl. 1. J.M. Bower, ed. Academic Press, San Diego, CA., 1996. pp. 317-322.
(.edu-paper.ps.Z)

3. BartSejn96b

Bartlett, M.S. and Sejnowski, T.J. (1996 b).
Learning Viewpoint Invariant Representations of Faces in an Attractor Network
Poster presented at the 18th Cognitive Science Society Meeting, San Diego, CA, July 12-15.
(.edu-paper.ps.Z)

4. BartSejn97

Bartlett, M.S. and Sejnowski, T.J. (1997).
Viewpoint invariant face recognition using independent component analysis and attractor networks
In M. Mozer, M. Jordan, T. Petsche (Eds.), Advances in Neural Information Processing Systems 9, MIT Press, Cambridge, MA. pp. 817-823.
(.edu-paper.ps)

5. BartSejn98

Bartlett, M.S. and Sejnowski, T.J. (1998).
Learning Viewpoint Invariant Face Representations from Visual Experience by Temporal Association
In H. Wechsler, P.J. Phillips, V. Bruce, S. Fogelman-Soulie, T. Huang (Eds.), Face Recognition: From Theory to Applications, NATO ASI Series F. Springer-Verlag.
(.edu-paper.ps)

6. Beck93

Becker, S. (1993).
Learning to Categorize Objects Using Temporal Coherence
In Advances in Neural Information Processing Systems 5, by Hanson, S.J., Cowan, J.D., and Giles, C.L., (eds.), pp. 361-368, San Mateo, CA: Morgan Kaufmann Publishers.
(.ca-paper.ps.gz)

7. Beck96

Becker, S. (1996).
Mutual Information Maximization: Models of Cortical Self-Organization
Network: Computation in Neural Systems, 7(1):7-31.
(.ca-abstract.html, .ca-paper.ps.gz)

8. Beck97

Becker, S. (1997).
Learning temporally persistent hierarchical representations
In Advances in Neural Information Processing Systems 9, by Mozer, M., Jordan, M., and Petsche, T. (eds.), MIT Press, Cambridge, MA, pages 824-830.

9. Beck99

Becker, S. (15. February 1999).
Implicit Learning in 3D Object Recognition: The Importance of Temporal Context
Neural Computation, 11(2):347-374.
(.ca-abstract.html, .ca-paper.ps.gz)

10. BeckHint92a

Becker, S. and Hinton, G.E. (1992 a).
A Self-Organizing Neural Network that Discovers Surfaces in Random-Dot Stereograms
Nature, 355(6356):161-163.
(.ca-abstract.html)

11. BeckHint92b

Becker, S. and Hinton, G.E. (1992 b).
Learning to Make Coherent Predictions in Domains with Discontinuities
In Advances in Neural Information Processing Systems 4, Morgan Kaufmann Publishers, pp. 372-379.
(.ca-paper.ps.gz)

12. BeckHint93

Becker, S. and Hinton, G.E. (1993).
Learning Mixture Models of Spatial Coherence
Neural Computation, 5(2):267-277.
(.ca-abstract.html)

13. BeckHint95

Becker, S. and Hinton, G.E. (1995).
Spatial coherence as an internal teacher for a neural network
in Backpropagation: Theory, Architectures, and Applications, Y. Chauvin and D. Rumelhart (eds), part of the series Developments in Connectionist Theory, Hillsdale, NJ: Lawrence Erlbaum.
(.ca-abstract.html, .ca-paper.ps.gz)

14. EdelWein91.

Edelman, S. and Weinshall, D. (1991).
A self-organizing multiple-view representation of 3D objects
Biological Cybernetics, 64(3):209-219.

15. EgleBraySton97

Eglen, S., Bray, A.J., and Stone, J.V. (1997).
Unsupervised Discovery of Invariances
Network: Computation in Neural Systems, 8(4):441-452.
(.uk-paper.ps.gz, .uk-paper.ps.gz)

16. EgleStonBarr96.

Eglen, S., Stone, J.V., and Barrow, H.G. (1996).
Learning perceptual invariances: A spatial model
Technical Report CSRP 404, School of Cognitive and Computing Sciences, University of Sussex.

17. EinhKaysKöni+02

Einhäuser, W., Kayser, C., König, P., and Körding, K.P. (February 2002).
Learning the invariance properties of complex cells from natural stimuli
European Journal of Neuroscience, 15(3):475-486.
(.com-paper.pdf)

18. Eise97

Eisele, M. (1997).
Unsupervised Learning of Temporal Constancies by Pyramidal-Type Neurons
In Mathematics of Neural Networks, Ellacott, Stephen W., Mason, John C., Anderson, Iain J. eds., Kluwer Academic Publishers, pp. 171-175.

19. Föld91

Földiák, P. (1991).
Learning Invariance from Transformation Sequences
Neural Computation, 3(2):194-200.
(two layer architecture: 1. simple cell layer with straight lines moving across; 2. complex cell layer trained with competitive learning based on activity traces)

20. Föld98.

Földiák, P. (1998).
Learning constancies for object perception
In Visual Constancies: Why things look as they do., Walsh, V. and Kulikowski, J.J., eds., Cambridge Univ. Press, Cambridge, U.K., in press.

21. Fuku99

Fukushima, K. (1999).
Self-organization of shift-invariant receptive fields
Neural Networks, 12(6):791-801.
(three layer architecture: 1. input layer with straight lines sweeping across; 2. simple cell layer with competitive learning; 3. complex cell layer with competitive learning based on output traces)

22. GrinTsodAmit93.

Griniasty, M., Tsodyks, M.V., and Amit, D.J. (1993).
Conversion of Temporal Correlations Between Stimuli to Spatial Correlations Between Attractors
Neural Computation, 5(1):1-17.

23. Hint87

Hinton, G.E. (1987).
Learning Translation Invariant Recognition in a Massively Parallel Network
In PARLE: Parallel Architectures and Languages Europe by Goos, G. and Hartmanis, J. (eds.), Lecture Notes in Computer Science, Springer-Verlag, Berlin, pp. 1-13,.
(four layer backpropagation network learning translation invariant recognition of small binary patterns, generalization of training patterns to new positions)

24. Hint89

Hinton, G.E. (1. September 1989).
Connectionist Learning Procedures
Artificial Intelligence, 40(1-3):185-234.
(On page 208 this paper includes one paragraph on temporal smoothness as a possible objective for learning.)

25. HintBeck90.

Hinton, G.E. and Becker, S. (1990).
An Unsupervised Learning Procedure that Discovers Surfaces in Random-Dot Stereograms
Proceedings of the International Joint Conference on Neural Networks, Washington, DC, January, Vol. 1, pp. 218-222, Lawrence Erlbaum Associates, Hillsdale, NJ.

26. KaysEinhDümm+01

Kayser, C., Einhäuser, W., Dümmer, O., König, P., and Körding, K.P. (2001).
Extracting slow subspaces from natural videos leads to complex cells
Proc. International Conference on Artificial Neural Networks (ICANN).

27. Koho96

Kohonen, T. (1996).
Emergence of Invariant-Feature Detectors in the Adaptive-Subspace SOM
Biological Cybernetics, 75(4):281-291.
(.com-Abstract, .com-Paper.pdf?)

28. KohoKaskLapp97

Kohonen, T., Kaski, S., and Lappalainen, H. (1997).
Self-Organized Formation of Various Invariant-Feature Filters in the Adaptive-Subspace SOM
Neural Computation, 9(6):1321-1344.
(.fi-abstract)

29. KördKöni01

Körding, K.P. and König, P. (December 2001).
Neurons with two sites of synaptic integration learn invariant representations
Neural Computation, 13(12):2823-2849.
(.org-Abstract, .org-Paper?, .org-Paper?)

30. Mitc91

Mitchison, G. (1991).
Removing Time Variation with the Anti-Hebbian Differential Synapse
Neural Computation, 3(3):312-320.
(includes a bias term to select among equivalent invariants)

31. OReilJohn93.

O'Reilly, R.C. and Johnson, M.H. (1993).
Object Recognition and Sensitive Periods: A Computational Analysis of Visual Imprinting
Department of Psychology, University of Colorado, Boulder, CO, Technical Report PDP.CNS.93.1.
(.edu-abstract, .edu-paper.ps.Z)

32. OReilJohn94

O'Reilly, R.C. and Johnson, M.H. (1994).
Object Recognition and Sensitive Periods: A Computation Analysis of Visual Imprinting
Neural Computation, 6(3):357-389.

33. OReilMClel92.

O'Reilly, R.C. and McClelland, J.L. (1992).
The Self-Organization of Spatially Invariant Representations
Department of Psychology, University of Colorado, Boulder, CO, Technical Report PDP.CNS.92.5.
(.edu-abstract, .edu-paper.ps.Z)

34. OramFöld96.

Oram, M.W. and Földiák, P. (1996).
Learning generalization and localization: Competition for stimulus type and receptive field
Neurocomputing, 11(2-4):297-321.

35. PargRoll98

Parga, N. and Rolls, E.T. (1998).
Transform-Invariant Recognition by Association in a Recurrent Network
Neural Computation, 10(6):1507-1525.

36. PengShaGan+98a

Peng, H.C., Sha, L.F., Gan, Q., and Wei, Y. (1998 a).
Energy function for learning invariance in multilayer perceptron
Electronics Letters, 34(3):292-294.

37. PengShaGan+98b

Peng, H.C., Sha, L.F., Gan, Q., and Wei, Y. (1998 b).
Combining adaptive sigmoid packet and trace neural network for fast invariance-learning
Electronics Letters, 34(9):898-900.

38. RaoBall98

Rao, R.P.N. and Ballard, D.H. (1998).
Development of localized oriented receptive fields by learning a translation-invariant code for natural images
Network: Computation in Neural Systems, 9(2):219-234.
(.edu-paper.pdf.gz)

39. Roll94.

Rolls, E.T. (1994).
Brain mechanisms for invariant visual recognition and learning
Behavioural Processes, 3:1134-1138.

40. Roll95.

Rolls, E.T. (1995).
Learning mechanisms in the temporal lobe visual cortex
Behavioural Brain Research, 66:177-185.

41. RollTove94.

Rolls, E.T. and Tovée, M.J. (1994).
Processing speed in the cerebral cortex, and the neurophysiology of visual backward masking
Proceedings of the Royal Society of London, Series B, 257:9-15.

42. SchrSejn92

Schraudolph, N.N. and Sejnowski, T.J. (1992).
Competitive Anti-Hebbian Learning of Invariants
In Moody, J.E., Hanson, S.J., and Lippmann, R.P., editors, Advances in Neural Information Processing Systems 4, Morgan Kaufmann, San Mateo, pp. 1017-1024.
(.ch-paper.ps.gz)

43. Spra05

Spratling, M.W. (2005).
Learning viewpoint invariant perceptual representations from cluttered images
IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5):753-761.

44. Ston94.

Stone, J.V. (1994).
Learning Spatio-temporal Invariances
Proceedings of British Machine Vision Conference, York, pp. 681-690.

45. Ston95a.

Stone, J.V. (1995 a).
Learning Spatio-temporal Invariances
Neural Computation and Psychology Proceedings of the 3rd Neural Computation and Psychology Workshop (NCPW3), Stirling, Scotland, 31 August-2 September 1994, editors L.S. Smith and P.J.B. Hancock. Springer Verlag: Workshops in Computing Series, April 1995.

46. Ston95b:

Stone, J.V. (1995 b).
Learning Spatio-Temporal Invariances
In Smith, L.S. and Hancock, P.J.B., eds., Neural Computation and Psychology (Workshop in Computing Series), pp. 75-85, Springer, Berlin.

47. Ston95c.

Stone, J.V. (1995 c).
Hierarchical Learning of Spatio-Temporal Invariances
International Conference on Artificial Neural Networks, June, Cambridge, pp 110-115.

48. Ston95d.

Stone, J.V. (1995 d).
Learning Visual Invariances Through Spatio-Temporal Constraints
Applied Vision Association Annual Meeting, "Invariance and Constancy in Vision" Workshop, Reading, April.

49. Ston96a

Stone, J.V. (1. October 1996 a).
Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints
Neural Computation, 8(7):1463-1492.
(.uk-paper.ps.gz)

50. Ston96b

Stone, J.V. (1996 b).
Learning Stereo Disparity Using Temporal Smoothness Constraints: A Computational Model
Spatial Vision, 10(1):15-29.
(.uk-paper.ps.gz)

51. Ston96c

Stone, J.V. (1996 c).
A Canonical Microfunction For Learning Perceptual Invariances
Perception, 25:207-220.
(.uk-paper.ps.gz)

52. StonBray95a

Stone, J.V. and Bray, A.J. (1995 a).
A Learning Rule for Extracting Spatio-Temporal Invariances
Network: Computation in Neural Systems, 6(3):429-436.
(.uk-paper.ps.gz)

53. StonBray95b.

Stone, J.V. and Bray, A.J. (1995 b).
Extracting Temporal Invariances
International Workshop on Artificial Neural Networks, Malaga, June.

54. StriRoll02

Stringer, S.M. and Rolls, E.T. (November 2002).
Invariant Object Recognition in the Visual System with Novel Views of 3D Objects
Neural Computation, 14(11):2585-2596.
(.org-Abstract, .org-Paper?, .org-Paper?)

55. Wall96

Wallis, G. (1996).
Using spatio-temporal correlations to learn invariant object recognition
Neural Networks, 9(9):1513-1519.

56. WallBadd97

Wallis, G. and Baddeley, R. (1997).
Optimal, Unsupervised Learning in Invariant Object Recognition
Neural Computation, 9(4):883-894.
(.de-abstract.html)

57. WallRoll96.

Wallis, G. and Rolls, E.T. (1996).
A model of invariant object recognition in the visual system
Technical Report, Oxfort University, Department of Experimentatl Psychology.

58. WallRoll97

Wallis, G. and Rolls, E.T. (1. February 1997).
Invariant Face and Object Recognition in the Visual System
Progress in Neurobiology, 51(2):167-194.
(.au-abstract)

59. WallRollFöld93

Wallis, G., Rolls, E.T., and Földiák, P. (1993).
Learning Invariant Responses to the Natural Transformations of Objects
In Proceedings of 1993 International Joint Conference on Neural Networks, Nagoya, Japan, 25-29 Oct., pp. 1087-1090.

60. Webb91

Webber, C.J.S.C. (1991).
Self-Organization of Position- and Deformation-Tolerant Neural Representations
Network: Computation in Neural Systems, 2(1):43-61.

61. Webb94

Webber, C.J.S.C. (1994).
Self-Organisation of Transformation-Invariant Detectors for Constituents of Perceptual Patterns
Network: Computation in Neural Systems, 5:471-496.

62. Webb00.

Webber, C.J.S.C. (2000).
Self-organisation of symmetry networks: Transformation invariance from the spontaneous symmetry-breaking mechanism
Neural Computation, 12(3):565-596.

63. WiskSejn02

Wiskott, L. and Sejnowski, T.J. (2002).
Slow Feature Analysis: Unsupervised Learning of Invariances
Neural Computation, 14(4):715-770.
(.org-Abstract, .de-abstract.html, .org-Paper?, .de-paper.ps.gz)

64. ZemeHint91a.

Zemel, R.S. and Hinton, G.E. (1991 a).
Discovering Viewpoint Invariant Relationships that Characterize Objects
Tech. Rep., Department of Computer Science, University of Toronto, Toronto, Canada.

65. ZemeHint91b

Zemel, R.S. and Hinton, G.E. (1991 b).
Discovering Viewpoint-Invariant Relationships that Characterize Objects
In Lippmann, R.P., Moody, J.E., and Touretzky, D.S., eds., Advances in Neural Information Processing Systems 3, pp. 299-305, Denver, Morgan Kaufmann, Mateo.

Author Index

46 authors, 23 (50%) with homepage. First author references are printed boldface.

Year Index

Journal Index

The numbers in the columns `R', `A', and `P' indicate the year from which on you can expect to find online references, abstracts, and papers, respectively. A '?' indicates documents, that may be accessible only to subscribers.

16 journals, 12 (75%) with homepage.