Abstract
A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization methods can help to solve this problem. In this work we compare different evolutionary optimization approaches for a biologically inspired neural vision system: Direct coding versus a biologically more plausible indirect coding using unsupervised local learning. A comparison to state-of-the-art recognition approaches shows the competitiveness of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2(11), 1019–1025 (1999)
Barlow, H.B.: The twelfth Bartlett memorial lecture: The role of single neurons in the psychology of perception. Quart. J. Exp. Psychol. 37, 121–145 (1985)
Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research 37, 3311–3325 (1997)
Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems 4, 461–476 (1990)
Rolls, E.T., Stringer, S.M.: On the design of neural networks in the brain by genetic evolution. Progress in Neurobiology 6(61), 557–579 (2000)
Sendhoff, B., Kreutz, M.: A model for the dynamic interaction between evolution and learning. Neural Processing Letters 10(3), 181–193 (1999)
Quartz, S., Sejnowski, T.: The neural basis of cognitive development: A constructivist manifesto. Behavioral and Brain Sciences 9, 537–596 (1997)
Rust, A.G., Adams, R., George, S., Bolouri, H.: Towards computational neural systems through developmental evolution. In: Wermter, S., Austin, J., Willshaw, D.J. (eds.) Emergent Neural Computational Architectures Based on Neuroscience. LNCS (LNAI), vol. 2036, pp. 188–202. Springer, Heidelberg (2001)
Wersing, H., Körner, E.: Learning optimized features for hierarchical models of invariant recognition. Neural Computation 15(7), 1559–1588 (2003)
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cyb. 39, 139–202 (1980)
Schwefel, H.-P., Rudolph, G.: Contemporary evolution strategies. In: Morán, F., Merelo, J.J., Moreno, A., Chacon, P. (eds.) ECAL 1995. LNCS, vol. 929, pp. 893–907. Springer, Heidelberg (1995)
Hyvärinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Computation 9(7), 1483–1492 (1997)
Wersing, H., Körner, E.: Unsupervised learning of combination features for hierarchical recognition models. In: Icann, J.R.D., et al. (eds.) Int. Conf. Artif. Neur. Netw., pp. 1225–1230. Springer, Heidelberg (2002)
Nayar, S.K., Nene, S.A., Murase, H.: Real-time 100 object recognition system. In: Proc. of ARPA Image Understanding Workshop, Palm Springs (1996)
Roobaert, D., Hulle, M.V.: View-based 3d object recognition with support vector machines. In: Proc. IEEE Int. Workshop on Neural Networks for Signal Processing, Madison, pp. 77–84. IEEE, New York (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schneider, G., Wersing, H., Sendhoff, B., Körner, E. (2004). Coupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model. In: Yao, X., et al. Parallel Problem Solving from Nature - PPSN VIII. PPSN 2004. Lecture Notes in Computer Science, vol 3242. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30217-9_67
Download citation
DOI: https://doi.org/10.1007/978-3-540-30217-9_67
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23092-2
Online ISBN: 978-3-540-30217-9
eBook Packages: Springer Book Archive