Abstract
This paper proposes a two layer modular neural system. The basic building blocks of the architecture are multilayer perceptrons trained with the backpropagation algorithm. Due to the proposed modular architecture the number of weight connections is less than in a fully connected multilayer perceptron. The modular network is designed to combine two different approaches of generalization known from connectionist and logical neural networks; this enhances the generalization abilities of the network. The architecture introduced here is especially useful in solving problems with a large number of input attributes.
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
I. Aleksander and H. Morton. An Introduction to Neural Computing. Chapman & Hall, second edition, 1995.
R. Bellotti, M. Castellano, C. De Marzo, and G. Satalino. Signal/background classification in a cosmic ray space experiment by a modular neural system. In Proc. of the SPIE — The International Society for Optical Engineering, volume 2492, pages 1153–1161. Springer-Verlag, 1995.
T. Kohonen, G. Barna, and R. Chrisley. Statistical pattern recognition with neural networks: benchmarking studies. In Proc. IEEE International Conference on Neural Networks, pages 61–67. San Diego, 1988.
L. Mui, A. Agarwal, A. Gupta, and P. Shen-Pei Wang. An adaptive modular neural network with application to unconstrained character recognition. International Journal of Pattern Recognition and Artificial Intelligence, 8(5):1189–1204, October 1994.
University of Stuttgart. Picture directory. FTP from ftp.uni-stuttgart.de, /pub/graphics/pictures and tv_film/staxtrek/next-gen/portrait.
D. E. Rumelhart, G. E. Hinton, and R. J. Williams. Learning internal representations by error propagation, volume I: Foundations. MIT Press, Cambridge, MA, 1986.
J. V. Stone and C. J. Thorton. Can Artificial Neural Networks Discover Useful Regularities?, pages 201–205. 1995. Conference Publication No. 409 IEE. 26–28 June 1995.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Wien
About this paper
Cite this paper
Schmidt, A., Bandar, Z. (1998). A Modular Neural Network Architecture with Additional Generalization Abilities for Large Input Vectors. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6492-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6492-1_8
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83087-1
Online ISBN: 978-3-7091-6492-1
eBook Packages: Springer Book Archive