Abstract
In this article we present an algorithm that permits training networks that include gaussian type higher order synapses. This algorithm is an extension of the classical backpropagation algorithm. Higher order synapses permit carrying out tasks using simpler networks than traditionally employed. The key to this simplicity is in the structure of the synapses: a gaussian with three trainable parameters. The fact that it is a function and consequently presents a variable output depending on its inputs and that it possesses more than one trainable parameter that allows it to implement non linear processing functions on its inputs, endows the networks with a large capacity for learning and generalization. We present two examples where these capacities are shown. The first one is a target tracking module for a the visual system of a real robot and the second one is an image classification system working on real images.
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.
References
Bianchini, M., Frasconi, P., Gori, M.: Learning without Local Minima in Radial Basis Function Networks. IEEE Transactions on Neural Networks, Vol. 6 (1995) 749–755
Chen, T., Chen, H.: Approximation Capability to Functions of Several Variables, Nonlinear Functionals and Operators by Radial Basis Function Neural Networks. IEEE Transactions on Neural Network, Vol. 6 (1995) 904–910
Giles, L., Maxwell, T.: Learning Invariance and Generalization in Higher Order Neural Networks. Applied Optics, Vol. 26, No. 23 (1987) 4972–4978
Rumelhart, D.E., Hinton, G.E., Willians, R.J.: Learning Internal Representations by Error Propagation. Parallel Distributed Processing, Explorations in the Microstructure of Cognition. MIT Press, Cambridge, Vol. I (1986) 318–326
Land, M.F., Collett, T.S.: A Survey of Active Vision in Invertebrates. In Srinavasan, M.V., Venkatesh, S. (eds.). From Living Eyes to Seeing Machines. Oxford University Press (1997) 16–36
Cliff, D.: Neural networks for visual tracking in an artificial fly. In Varela, F.J., Bourgine, P. (eds.): Toward a Practice of Autonomous Systems. Proceedings of the First European Conference on Artificial Life. Paris, France, Dec. 1991. Cambridge, MA, USA: MIT Press (1992) 78–87
Missler, J.M., Kamangar, F.A.: A Neural Network for Pursuit Tracking Inspired by the Fly Visual System. Neural Networks, Vol. 8. No. 3 (1995) 463–480
Srinivasan, M.V.: Strategies for Visual Navigation, Target Detection and Camouflage: Inspirations from Insect Vision. Proceedings of ICNN’95-International Conference on Neural Networks,Perth, WA, Australia, Vol. 5. New York, NY, USA: IEEE, (1995) 2456–2460
Neubauer, C.: Evaluation of Convolutional Neural Networks for Visual Recognition. IEEE Transactions on Neural Networks, Vol. 9. No. 4 (1998) 685–696
Gori, M., Scarselli, F.: Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification?. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20. No. 11 (1998) 1121–1132
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Duro, R.J., Crespo, J.L., Santos, J. (1999). Training higher order Gaussian synapses. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098211
Download citation
DOI: https://doi.org/10.1007/BFb0098211
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive