Abstract
In this paper we study the time complexity of learning in terms of continuous-parametric representations (CPR) of concept classes, that underly most of the connectionist approaches to machine learning. We introduce the notion of non-suspect concept classes in CPR. Suspiciousness essentially qualifies the shape of the error function associated to a CP representation when the learner adopts an optimization algorithm for searching in the parameter space. We show that a concept class F is non-suspect in a CPR only if F is efficiently learnable. Under some further assumptions, that are met for example in the case of the class of linearly separable patterns, we claim that there exists an optimal algorithm for learning non-suspect concept classes in the representation of multilayered neural networks, whose time complexity is Θ(mp), being m the number of training examples and p the dimension of the parameter space.
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
J. Judd, Neural Network Design and the Complexity of Learning. Cambridge, London: The MIT Press, 1990.
A. Blum and R. Rivest, “Training a 3-node neural net is NP-complete,” in Advances in Neural Information Processing Systems (D. Touretzky, ed.), vol. 1, pp. 494–501, Morgan Kaufmann, San Mateo, 1989.
B. Natarajan, Machine Learning: A Theoretical Approach. San Mateo, CA: Morgan Kaufmann Publishers, Inc., 1991.
P. Prasconi, S. Fanelli, M. Gori, and M. Protasi, “Suspiciousness of loading problems,” in IEEE International Conference on Neural Networks, pp. II 1240–1245, IEEE Press, 9–12 June 1997.
S. Fanelli, P. Frasconi, M. Gori, and M. Protasi, “Computational suspiciousness of learning in artificial neural networks,” Tech. Rep. TR-DII-13-98, Dipartimento di Ingegneria dell’Informazione, Univ. di Siena, 1998.
E. Sontag and H. Sussman, “Backpropagation separates when perceptrons do,” in International Joint Conference on Neural Networks, vol. 1, (Washington DC), pp. 639–642, IEEE Press, June 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Fanelli, S., Frasconi, P., Gori, M., Protasi, M. (1999). Computational Suspiciousness of Learning in Artificial Neural Nets. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-98. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0811-5_2
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0811-5_2
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1208-2
Online ISBN: 978-1-4471-0811-5
eBook Packages: Springer Book Archive