Abstract
Computer vision researchers have only comparatively recently begun to acknowledge the behavioural contexts of vision. So-called animate vision has a number of advantages over the inanimate paradigm. This paper reviews an ongoing project in animate vision using neural networks. The project has a novel context: it involves the simulation of a hoverfly, with the neural network acting as a closed-loop controller for the simulated fly. The underlying thesis of this work is that most neural network models which do not recognise the behavioural contexts of neural computation are of limited interest. This stance places the model within the domain of “computational neuroethology”, rather than “computational neuroscience”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
E. H. Adelson and J. R. Bergen. Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A, 2(2):284–299, February 1985.
M. A. Arbib. Levels of modelling of mechanisms of visually guided behaviour. The Behavioral and Brain Sciences, 10:407–465, 1987.
D. H. Ballard. Eye movements and spatial cognition. TR 218, University of Rochester Computer Science Department, November 1987.
D. H. Ballard. Reference frames for animate vision. In Proc. IJCAI, pages 1635–1641, 1989.
R. A. Brooks. A robust layered control system for a mobile robot. A.I. Memo 864, M.I.T. A.I. Lab, September 1985.
C. M. Brown. Predictive gaze control. In Proceedings of the Fifth Alvey Vision Conference, pages 103–108, 1989.
C. M. Brown, editor. The Rochester Robot. TR 257, University of Rochester Computer Science Department, August 1988.
V. Bruce and P. R. Green. Visual Perception: physiology, psychology and ecology. Lawrence Erlbaum Associates, London, 1985.
J. M. Camhi. Neuroethology: Nerve Cells and the Natural Behaviour of Animals. Sinauer Associates Inc., Sunderland, Mass., 1984.
D. T. Cliff. The computational hoverfly; a study in computational neuroethology. In J.-A. Meyer and S. W. Wilson, editors, From Animals to Animats: Proceedings of the First International Conference on the Simulation of Adaptive Behaviour, Cambridge MA, 1990. M.I.T. Press — Bradford Books.
D. T. Cliff. Computational neuroethology: A provisional manifesto. CSRP 162, University of Sussex School of Cognitive and Computing Sciences, May 1990.
D. T. Cliff. Computational neuroethology: A provisional manifesto. In J.-A. Meyer and S. W. Wilson, editors, From Animals to Animats: Proceedings of the First International Conference on the Simulation of Adaptive Behaviour, Cambridge MA, 1990. M.I.T. Press — Bradford Books.
D. T. Cliff. Network control for animate vision with nonuniform sampling. CSRP 163, University of Sussex School of Cognitive and Computing Sciences, 1990. Forthcoming.
T. S. Collett. Some operating rules for the optomotor system of a hoverfly during voluntary flight. Journal of Comparative Physiology A, 138:271–282, 1980.
T. S. Collett and A. J. King. Vision during flight. In G. A. Horridge, editor, The compound eye and vision of insects, pages 437–466. Clarendon, Oxford, 1975.
T. S. Collett and M. F. Land. Visual control of flight behaviour in the hoverfly, Syritta pipiens L. Journal of Comparative Physiology, 99:1–66, 1975.
F. Crick. The recent excitement about neural networks. Nature, 337:129–132, January 1989.
S. Harnad. The symbol grounding problem. In CNLS Conference on Emergent Computation, Los Alamos, May 1989. Submitted to Physica D.
D. Hearn and P. M. Baker. Computer Graphics. Prentice Hall International, Englewood Cliffs NJ, 1986.
G. E. Hinton and S. Becker. An unsupervised learning procedure that discovers surfaces in random-dot stereograms. In International Joint Conference on Neural Networks, Washington DC, January 1990.
G. Hoyle. The scope of neuroethology. The Behavioral and Brain Sciences, 7:367–412, 1984.
M. F. Land. Similarities in the visual behaviour of arthropods and men. In M. S. Gazzaniga and C. Blakemore, editors, Handbook of Psychobiology, pages 49–72. Academic Press, New York, 1975.
R. Linsker. Designing a sensory processing system: What can be learned from principle component analysis? Research Report RC 14983, I.B.M. T. J. Watson Research Centre, Yorktown Heights, NY, September 1989.
R. Linsker. How to generate ordered maps by maximising the mutual information between input and output signals. Research Report RC 14624, I.B.M. T. J. Watson Research Centre, Yorktown Heights, NY, May 1989.
M. R. Lynch and P. J. Rayner. The properties and implementation of the nonlinear vector space connectionist model. In First IEE International Conference on Artificial Neural Networks, pages 186–190, London, October 1989. IEE.
D. Marr. Vision. W. H. Freeman, New York, 1982.
G. Mather, B. Moulden, and A. O’Halloran. Polarity specific adaptation to motion: evidence for gradient detectors, 1990. preprint.
J.-A. Meyer and S. W. Wilson, editors. From Animals to Animais: Proceedings of the First International Conference on the Simulation of Adaptive Behaviour. M.I.T. Press — Bradford Books, Cambridge MA, 1990.
D. Parisi, F. Cecconi, and S. Nolfi. Econets: Neural networks that learn in an environment. Network, 1:149–168, 1990.
M. G. Paulin, M. E. Nelson, and J. M. Bower. Dynamics of compensatory eye movement control: An optimal estimation analysis of the vestibulo-ocular reflex. International Journal of Neural Systems, 1(1):23–29, 1989.
T. Poggio and F. Girosi. A theory of networks for approximation and learning. A.I. Memo 1140, M.I.T. A.I. Lab, July 1989.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation. In D. E. Rumelhart and J. L. McClelland, editors, Parallel Distributed Processing, Volume 1: Foundations, pages 318–362. M.I.T. Press — Bradford Books, Cambridge MA, 1986.
T. J. Sejnowski, C. Koch, and P. S. Churchland. Computational neuroscience. Science, 241:1299–1306, September 1988.
M. V. Srinivasan, S. B. Laughlin, and A. Dubs. Predictive coding: a fresh view of inhibition in the retina. Proc. R. Soc. Lond. B, 216:427–459, 1982.
J. P. H. van Santen and G. Sperling. Elaborated Reichardt detectors. Journal of the Optical Society of America A, 2(2):300–320, February 1985.
A. B. Watson. Detection and recognition of simple spatial forms. In O. J. Braddick and A. C. Sleigh, editors, Physical and Biological Processing of Images, pages 100–114. Springer-Verlag, Berlin, 1983.
H. White. Learning in artificial networks: A statistical perspective. Neural Computation, 1:415–424, 1989.
S. W. Wilson. Adaptive “cortical” pattern recognition. In Proceedings of the International Conference on Genetic Algorithms and Their Application, Pittsburg, PA, July 1985.
D. S. Young. Logarithmic sampling of images for computer vision. In A. G. Cohn, editor, Proceedings of the Seventh conference of the Society for the Study of Artificial Intelligence and Simulation of Behaviour, pages 145–150, London, April 1989. Pitman/Morgan Kaufmann.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag London Limited
About this paper
Cite this paper
Cliff, D. (1991). Neural Networks and Visual Behaviour: Flies; Panned Eyes; and Statistics. In: Steels, L., Smith, B. (eds) AISB91. Springer, London. https://doi.org/10.1007/978-1-4471-1852-7_8
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1852-7_8
Publisher Name: Springer, London
Print ISBN: 978-3-540-19671-6
Online ISBN: 978-1-4471-1852-7
eBook Packages: Springer Book Archive