Abstract
In contrast to many Artificial Neural Network models, the human visual system operates in a mixed parallel-sequential mode: Signals are transmitted in parallel from many areas of the retina towards the brain. In addition, the retina — by moving the eyes or the whole head or the whole body — is directed towards different parts of the environment in sequence. The aim of this project was to create a neural network learning model that has both parallel and sequential aspects. The network learns to focus an attentional window at important, discriminative areas of patterns it is learning to recognise. One advantage of the model is that it is able to learn to discriminate or to categorise patterns that differ from each other only in small areas. In such tasks it often performs better than straightforward backpropagation networks.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Bibliography
Bowles, A. (1992). Machine learns which features to select. In A. Adams & L. Sterling (Eds.), Proceedings of the 5th Australian Joint Conference on Artificial Intelligence (pp. 127–132). Singapore: World Scientific.
Bruce, V. (1988). Recognising faces. Hillsdale: Lawrence Erlbaum Associates.
Bruce, V., and Green, P.R. (1990). Visual perception. Physiology, psychology and ecology. Hillsdale: Lawrence Erlbaum Associates.
Carpenter, G. & Grossberg, S. (1988). The ART of adaptive pattern recognition by a self-organizing neural network. Computer, 21 (3), 77–88.
Hochberg, J. (1968). In the mind's eye. In R.N. Haber (Ed), Contemporary theory and research in visual perception. London: Holt, Rinehart, and Winston.
Kohonen, T. (1988). The “neural” phonetic typewriter. Computer, 21, 11–24.
Kruschke, J.K. (1992). ALCOVE: An exemplar-based connectionist model of category learning. Psychological Review, 99, 22–44.
LeCun, Y. (1989). Generalization and network design strategies. In Pfeifer, R., Schreter, Z., Fogelman-Soulie, F.,& Steels, L. (Eds.). Connectionism in perspective. Amsterdam: Elsevier, 277–282.
Lovejoy, E. (1965). An attention theory of discrimination learning. Journal of Mathematical Psychology, 2, 342–362.
Mackintosh, N.J. (1965). Selective attention in animal discrimination learning. Psychological Review 64, 124–150.
Rumelhart, D., Hinton, G., & Williams, R.J. (1986). Learning internal representations by error propagation. In Rumelhart, D.E., McClelland, J.L. and the PDP Research Group (1986). Parallel Distributed Processing, vol.1, Foundations. Cambridge: MIT-Press, 318–362.
Schreter, Z. (1990). Modelling with connectionist networks: Interactions between cognition and arousal. Unpublished PhD Thesis, University of Zurich.
Schreter, Z. (1994). ASN, an attentional scanning network. Proceedings of ISANN 94, Tainan, Taiwan 259–264.
Schreter, Z., and Latimer, C.R. (1992). A connectionist model of attentional learning using a sequentially allocatable “spotlight of attention”. Proceedings of the Third Australian Conference on Neural Networks (ACNN'92). Canberra, 1992, 143–146.
Sperling, G. (1960). The information available in brief visual presentations. Psychological Monographs, 74, whole no. 498.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schreter, Z. (1995). Learning by attentional scanning. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_214
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_214
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive