Abstract
The advantages of Variable Step Search algorithm - a simple local search-based method of MLP training is that it does not require differentiable error functions, has better convergence properties than backpropagation and lower memory requirements and computational cost than global optimization and second order methods. However, in some applications, the issue of training time reduction becomes very important. In this paper we evaluate several approaches to achieve this reduction.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Aarts, E., Lenstra, J.K.: Local Search in Combinatorial Optimization. John Wiley & Sons, Inc., New York (1997)
Du, K.-L., Swamy, M.-N.S.: Neural Networks and Statistical Learning. Springer (2013)
Garcia-Pedrajas, N., et al.: An alternative approach for neural network evolution with a genetic algorithm. Neural Networks 19(4), 514–528 (2006)
Engel, J.: Teaching Feed-forward Neural Networks by Simulated Annealing. Complex Systems 2, 641–648 (1988)
Battiti, R., Tecchiolli, G.: Training Neural Nets with the Reactive Tabu Search. IEEE Trans. on Neural Networks 6, 1185–1200 (1995)
Bengio, Y.: Learning Deep Architectures for AI. Foundations and Trends in Machine Learning 2(1), 1–127 (2009)
Beliakov, G., Kelarev, A., Yearwood, J.: Derivative-free optimization and neural networks for robust regression. Optimization 61(12), 1467–1490 (2012)
Burden, R.L., Douglas Faires, J.: Numerical Analysis, Cengage Learning (2010)
Kordos, M., Duch, W.: Variable Step Search Algorithm for Feedforward Networks. Neurocomputing 71(13-15), 2470–2480 (2008)
Kordos, M., Rusiecki, A.: Improving MLP Neural Network Performance by Noise Reduction. In: Dediu, A.-H., Martín-Vide, C., Truthe, B., Vega-Rodríguez, M.A. (eds.) TPNC 2013. LNCS, vol. 8273, pp. 133–144. Springer, Heidelberg (2013)
Rusiecki, A., Kordos, M., Kamiński, T., Greń, K.: Training Neural Networks on Noisy Data. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014, Part I. LNCS, vol. 8467, pp. 131–142. Springer, Heidelberg (2014)
Rusiecki, A.: Robust learning algorithm based on LTA estimator. Neurocomputing 120, 624–632 (2013)
Merz, C., Murphy, P.: UCI repository of machine learning databases (2014), http://www.ics.uci.edu/mlearn/MLRepository.html
Source code and datasets used in the paper, http://www.kordos.com/software/ideal2014.zip
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kordos, M., Rusiecki, A., Kamiński, T., Greń, K. (2014). Weight Update Sequence in MLP Networks. In: Corchado, E., Lozano, J.A., Quintián, H., Yin, H. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2014. IDEAL 2014. Lecture Notes in Computer Science, vol 8669. Springer, Cham. https://doi.org/10.1007/978-3-319-10840-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-10840-7_33
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10839-1
Online ISBN: 978-3-319-10840-7
eBook Packages: Computer ScienceComputer Science (R0)