Abstract
Recently, a convex incremental algorithm (CI-ELM) has been proposed in Huang and Chen (Neurocomputing 70:3056–3062, 2007), which randomly chooses hidden neurons and then analytically determines the output weights connecting with the hidden layer and the output layer. Though hidden neurons are generated randomly, the network constructed by CI-ELM is still based on the principle of universal approximation. The random approximation theory breaks through the limitation of most conventional theories, eliminating the need for tuning hidden neurons. However, due to the random characteristic, some of the neurons contribute little to decrease the residual error, which eventually increase the complexity and computation of neural networks. Thus, CI-ELM cannot precisely give out its convergence rate. Based on Lee’s results (Lee et al., IEEE Trans Inf Theory 42(6):2118–2132, 1996), we first show the convergence rate of a maximum CI-ELM, and then systematically analyze the convergence rate of an enhanced CI-ELM. Different from CI-ELM, the hidden neurons of the two algorithms are chosen by following the maximum or optimality principle under the same structure as CI-ELM. Further, the proof process also demonstrates that our algorithms achieve smaller residual errors than CI-ELM. Since the proposed neural networks remove these “useless” neurons, they improve the efficiency of neural networks. The experimental results on benchmark regression problems will support our conclusions.
Similar content being viewed by others
References
Huang, G.-B., Chen, L.: Convex incremental extreme learning machine. Neurocomputing 70, 3056–3062 (2007)
Lee, W.S., Bartlett, P.L., Williamson, R.C.: Efficient agnostic learning of neural networks with bounded fan-in. IEEE Trans. Inf. Theory 42(6), 2118–2132 (1996)
Ito, Y.: Approximation of functions on a compact set by finite sums of a sigmoid function without scaling. Neural Netw. 4, 817–826 (1991)
Leshno, M., Lin, V.Y., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a nonpolynomial activation function can approxiamate any function. Neural Netw. 6, 861–867 (1993)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4, 251–257 (1991)
Huang, G.-B., Chen, L., Siew, C.-K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw. 17(4), 879–892 (2006)
Jones, L.K.: A simple lemma on greedy approximation in hilbert space and convergence rates for projection pursuit regression and neural networks. Ann. Stat. 20(1), 608–613 (1992)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoid function. IEEE Trans. Inf. Theory 39(3), 930–945 (1993)
Kwok, T.-Y., Yeung, D.-Y.: Objective functions for training new hidden units in constructive neural networks. IEEE Trans. Neural Netw. 8(5), 1131–1148 (1997)
Meir, R., Maiorov, V.E.: On the optimality of neural-network approximation using incremental algorithms. IEEE Trans. Neural Netw. 11(2), 323–337 (2000)
Romero, E.: A new incremental method for function approximation using feed-forward neural networks. In: Proc. INNS-IEEE International Joint Conference on Neural Networks (IJCNN’2002), pp. 1968–1973. IEEE, Piscataway (2002)
Lavretsky, E.: On the geometric convergence of neural approximations. IEEE Trans. Neural Netw. 13(2), 274–282 (2002)
Voxman, W.L., Roy, J., Goetschel, H.: Advanced Calculus: An Introduction to Modern Analysis. Marcel Dekker, New York (1981)
LeCun, Y., Bottou, L., Orr, G.B., Müller, K.-R.: Efficient BackProp. Lect. Notes Comput. Sci. 1524, 9–50 (1998)
Drucker, H., Burges, C.J.C., Kaufman, L., Smola, A., Vapnik, V.: Support vector regression machines. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, p. 155. MIT, Cambridge (1997)
Platt, J.: A resource-allocating network for function interpolation. Neural Comput. 3, 213–225 (1991)
Yingwei, L., Saratchandran, P., Sundararajan, N.: A sequental learning scheme for function approximation using minimal radial basis function (rbf) neural networks. Neural Comput. 9, 461–478 (1997)
Blake, C., Merz, C.: UCI repository of machine learning databases. Department of Information and Computer Sciences, University of California, Irvine, USA. http://www.ics.uci.edu/∼mlearn/MLRepository.html (1998)
Author information
Authors and Affiliations
Corresponding author
Additional information
The work is under the funding of Singapore MOE AcRF Tier 1 grant WBS No: R 252-000-221-112.
Rights and permissions
About this article
Cite this article
Chen, L., Pung, H.K. Convergence analysis of convex incremental neural networks. Ann Math Artif Intell 52, 67–80 (2008). https://doi.org/10.1007/s10472-008-9097-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10472-008-9097-2