Abstract
Learning problems with inherent non-separable Boolean logic is still a challenge that has not been addressed by neural or kernel classifiers. The k-separability concept introduced recently allows for characterization of complexity of non-separable learning problems. A simple constructive feedforward network that uses a modified form of the error function and a window-like functions to localize outputs after projections on a line has been tested on such problems with quite good results. The computational cost of training is low because most nodes and connections are fixed and only weights of one node are modified at each training step. Several examples of learning Boolean functions and results of classification tests on real-world multiclass datasets are presented.
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
Iyoda, E., Nobuhara, H., Hirota, K.: A solution for the n-bit parity problem using a single translated multiplicative neuron. Neural Processing Letters 18(3), 233–238 (2003)
Stork, D.G., Allen, J.: How to solve the n-bit parity problem with two hidden units. Neural Networks 5, 923–926 (1992)
Wilamowski, B., Hunter, D.: Solving parity-n problems with feedforward neural network. In: IJCNN’03. Proc. of the Int. Joint Conf. on Neural Networks, Portland, Oregon, vol. I, pp. 2546–2551. IEEE Computer Society Press, Los Alamitos (2003)
Sahami, M.: Learning non-linearly separable boolean functions with linear threshold unit trees and madaline-style networks. In: National Conference on Artificial Intelligence, pp. 335–341 (1993)
Liu, D., Hohil, M.E., Smith, S.H.: N-bit parity neural networks: new solutions based on linear programming. Neurocomputing 48, 477–488 (2002)
Muselli, M.: Sequential constructive techniques. In: Leondes, C. (ed.) Optimization Techniques of Neural Network Systems, Techniques and Applications, vol. 2, pp. 81–144. Academic Press, San Diego, CA (1998)
Duch, W.: k-separability. In: Kollias, S., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 188–197. Springer, Heidelberg (2006)
Duch, W., Jankowski, N.: Survey of neural transfer functions. Neural Computing Surveys (1999)
Bengio, Y., Delalleau, O., Roux, N.L.: The curse of highly variable functions for local kernel machines. Advances in Neural Information Processing Systems 18, 107–114 (2006)
Bengio, Y., Monperrus, M., Larochelle, H.: Non-local estimation of manifold structure. Neural Computation 18, 2509–2528 (2006)
Duch, W.: Towards comprehensive foundations of computational intelligence. In: Duch, W., Mandziuk, J. (eds.) Challenges for Computational Intelligence, Springer, Heidelberg (in print, 2007)
Duch, W., Jankowski, N.: Taxonomy of neural transfer functions. In: International Joint Conference on Neural Networks, Como, Italy, vol. III, pp. 477–484. IEEE Computer Society Press, Los Alamitos (2000)
S.T., et al.: The monk’s problems: a performance comparison of different learning algorithms. Technical Report CMU-CS-91-197, Carnegie Mellon University (1991)
Duch, W., Adamczak, R., Gra̧bczewski, K.: A new methodology of extraction, optimization and application of crisp and fuzzy logical rules. IEEE Transactions on Neural Networks 12, 277–306 (2001)
Merz, C., Murphy, P.: UCI repository of machine learning databases (1998-2004), http://www.ics.uci.edu/~mlearn/MLRepository.html
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grochowski, M., Duch, W. (2007). Learning Highly Non-separable Boolean Functions Using Constructive Feedforward Neural Network. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74690-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-540-74690-4_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74689-8
Online ISBN: 978-3-540-74690-4
eBook Packages: Computer ScienceComputer Science (R0)