Abstract
This paper presents some complexity results for the specific case of a VLSI friendly neural network used in classification problems. A VLSI-friendly neural network is a neural network using exclusively integer weights in a narrow interval. The results presented here give updated worst-case lower bounds for the number of weights used by the network. It is shown that the number of weights can be lower bounded by an expression calculated using parameters depending exclusively on the problem (the minimum distance between patterns of opposite classes, the maximum distance between any patterns, the number of patterns and the number of dimensions). The theoretical approach is used to calculate the necessary weight range, a lower bound for the number of bits necessary to solve the problem in the worst case and the necessary number of weights for several problems. Then, a constructive algorithm using limited precision integer weights is used to construct and train neural networks for the same problems. The experimental values obtained are then compared with the theoretical values calculated. The comparison shows that the necessary weight precision can be estimated accurately using the given approach. However, the estimated numbers of weights are in general larger than the values obtained experimentally.
Preview
Unable to display preview. Download preview PDF.
References
Baffes, P.T., J.M. Zelle — Growing layers of perceptrons: introducing the extentron algorithm, Proc. of 1992 Intl. Joint Conf. on Neural Networks, II, pp. 392–397, IEEE Press, 1992.
Beiu V., Draghici S., Makaruk H.E. — On Limited Fan-in Optimal Neural Networks, Proc. of the IV Brazilian Symposium on Neural Networks, SBRN (Goiana, Brazil, 3–5 December, 1997). Also published as Technical Report LA-UR-97-1567, Los Alamos National Laboratories, 1997.
Coggins R., M. Jabri, Wattle: A Trainable Gain Analogue VLSI Neural Network, Advances in NIPS 6 (NIPS*93, Denver, CO), Morgan Kaufman, San Mateo, CA, 874–881, 1994.
Draghici S., Beiu, V. — Entropy based comparison of neural networks for classification, in Proc. of The 9-th Italian Workshop on Neural Nets, WIRN Vietri-sul-mare, 22–24 May, Springer-Verlag, 1997. Also published as Technical Report LA-UR-97-483, Los Alamos. National Laboratory, 1997.
Draghici S., Sethi, I.K: On the possibilities of the limited precision weights neural networks in classification problems, Proc. of International Work-Conference on Artificial and Natural Neural Networks IWANN'97, Lanzarote, Canary Islands, June 4–6, 1997.
Draghici S., Beiu V., Entropy based comparison of neural networks for classification, Proc. of The 9-th Italian Workshop on Neural Nets, WIRN Vietri-sul-mare, 22–24 May, 1997.
Draghici S., Sethi I.K. — Adapting theoretical constructive algorithms to hardware implementations for classification problems, Proc. of the International Conference on Engineering Applications of Neural Networks, Stockholm, Sweden, 16–18 June, 1997.
Dundar G., K. Rose, The Effect of Quantization on Multilayer Neural Networks, IEEE Transactions on Neural Networks 6 (6), pp. 1446–1451, 1995.
Hand D.J., Discrimination and Classification, John Wiley, 1981.
Hecht-Nielsen, R., Kolmogorov's mapping neural network existence theorem. Proc. of the IEEE Conference on Neural Networks III, pp. 11–13, New York, IEEE Press. 1987.
Hohfeld M., S.E. Fahlman, Learning with limited numerical precision using the Cascade-Correlation Algorithm, Tech.Rep. CMU-CS-91-130, School of Comp. Sci. Carnegie Mellon, May 1991. Also in IEEE Transactions on Neural Networks, NN-3(4), 602–611, 1992.
Hohfeld M., S.E. Fahlman, Probabilistic rounding in neural networks with limited precision. In U. Ruckert and J.A. Nossek (eds.): Microelectronics for Neural Networks (Proc. MicroNeuro'91 — Munich, Germany), Kyrill & Method Verlag, 1–8, October 1991. Also in Neurocomputing, 4, 291–299, 1992.
Hornik K., M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators, Neural Networks, vol. 2, pp. 359–366, 1989.
Homik K., Some new results on neural network approximation, Neural Networks, vol. 6, pp. 1069–1072,1993.
Khan A.H., E.L. Hines, Integer weight neural networks, Electronics Letters, 30 (15), pp. 1237–1238, 1994.
Khan A.H., R.G. Wilson, Integer weight approximation of continuous-weight multilayer feedforward nets, Proc. IEEE Int. Conf. on Neura. Networks, vol. 1, pp. 392–397, Washington DC, June 1996, IEEE Press, New York, NY, 1996.
Kurkova, V. — Kolmogorov's theorem and multilayer neural networks. Neural Networks 5, 501–506, 1992.
Kwan H.K., Tang C.Z., Designing Multilayer Feedforward Neural Networks Using Simplified Activation Functions and One-Power-of-Two Weights. Electronic Letters, 28 (25), pp. 2343–2344, 1992.
Kwan H.K., Tang C.Z., Multiplierless Multilayer Feedforward Neural Networks Design Suitable for Continuous Input-Output Mapping, Electronic Letters, 29 (14), pp. 1259–1260, 1993.
Marchesi M., G. Orlandi, F. Piazza, L. Pollonara, A. Uncini, Multilayer Perceptrons with Discrete Weights, Proc. Int. Joint Conf. on Neural Networks IJCNN'90, San Diego, Vol. II, pp. 623–630, June, 1990.
Marchesi M., G. Orlandi, F. Piazza, A. Uncini, Fast Neural Networks without Multipliers, IEEE Transactions on Neural Networks, NN-4 (1), pp. 53–62, 1993.
Tang C.Z., H.K. Kwan, Multilayer Feedforward Neural Networks with Single Power-ofTwo Weights. IEEE Trans. On Signal Processing, SP-41(8), 2724–2727, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Draghici, S. (1998). On the complexity of VLSI-friendly neural networks for classification problems. In: Mercer, R.E., Neufeld, E. (eds) Advances in Artificial Intelligence. Canadian AI 1998. Lecture Notes in Computer Science, vol 1418. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-64575-6_58
Download citation
DOI: https://doi.org/10.1007/3-540-64575-6_58
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64575-7
Online ISBN: 978-3-540-69349-9
eBook Packages: Springer Book Archive