Abstract
Neural networks use their hidden layers to transform input data into linearly separable data clusters, with a linear or a perceptron type output layer making the final projection on the line perpendicular to the discriminating hyperplane. For complex data with multimodal distributions this transformation is difficult to learn. Projection on k ≥2 line segments is the simplest extension of linear separability, defining much easier goal for the learning process. The difficulty of learning non-linear data distributions is shifted to separation of line intervals, making the main part of the transformation much simpler. For classification of difficult Boolean problems, such as the parity problem, linear projection combined with k-separability is sufficient.
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
Duda, R.O., Hart, P.E., Stork, D.: Patter Classification. J. Wiley & Sons, New York (2001)
Duch, W.: Similarity based methods: a general framework for classification, approximation and association. Control and Cybernetics 29, 937–968 (2000)
Duch, W., Adamczak, R., Diercksen, G.: Classification, association and pattern completion using neural similarity based methods. Applied Math. & Comp. Science 10, 101–120 (2000)
Witten, I., Frank, E.: Data Mining: Practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)
Jankowski, N., Gra̧bczewski, K., Duch, W., Naud, A.R.: Ghostminer data mining software. Technical report (2000-2005), http://www.fqspl.com.pl/ghostminer/
Stork, D., Allen, J.: How to solve the n-bit parity problem with two hidden units. Neural Networks 5, 923–926 (1992)
Minor, J.: Parity with two layer feedforward nets. Neural Networks 6, 705–707 (1993)
Setiono, R.: On the solution of the parity problem by a single hidden layer feedforward neural network. Neurocomputing 16, 225–235 (1997)
Lavretsky, E.: On the exact solution of the parity-n problem using ordered neural networks. Neural Networks 13, 643–649 (2000)
Arslanov, M., Ashigaliev, D., Ismail, E.: N-bit parity ordered neural networks. Neurocomputing 48, 1053–1056 (2002)
Liu, D., Hohil, M., Smith, S.: N-bit parity neural networks: new solutions based on linear programming. Neurocomputing 48, 477–488 (2002)
Torres-Moreno, J., Aguilar, J., Gordon, M.: The minimum number of errors in the n-parity and its solution with an incremental neural network. Neural Proc. Letters 16, 201–210 (2002)
Iyoda, E., Nobuhara, H., Hirota, K.: A solution for the n-bit parity problem using a single translated multiplicative neuron. Neural Processing Letters 18, 233–238 (2003)
Wilamowski, B., Hunter, D.: Solving parity-n problems with feedforward neural network. In: Int. Joint Conf. on Neural Networks (IJCNN 2003), Portland, Oregon, vol. I, pp. 2546–2551 (2003)
Duch, W.: Visualization of hidden node activity in neural networks: I. Visualization methods. II. Application to RBF networks. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 38–49. Springer, Heidelberg (2004)
Duch, W.: Coloring black boxes: visualization of neural network decisions. In: Int. Joint Conf. on Neural Networks, Portland, Oregon, vol. I, pp. 1735–1740. IEEE Press, Los Alamitos (2003)
Duch, W., Jankowski, N.: Survey of neural transfer functions. Neural Computing Surveys 2, 163–213 (1999)
Duch, W., Jankowski, N.: Taxonomy of neural transfer functions. In: International Joint Conference on Neural Networks, Como, Italy, vol. III, pp. 477–484. IEEE Press, Los Alamitos (2000)
Dietterich, T., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Journal Of Artificial Intelligence Research 2, 263–286 (1995)
Zuyev, Y.: Asymptotics of the logarithm of the number of threshold functions of the algebra of logic. Soviet Mathematics Doklady 39 (1989)
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)
Ngom, A., Stojmenovic, I., Zunic, J.: On the Number of Multilinear Partitions and the Computing Capacity of Multiple-Valued Multiple-Threshold Perceptrons. IEEE Transactions on Neural Networks 14, 469–477 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Duch, W. (2006). K-Separability. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_20
Download citation
DOI: https://doi.org/10.1007/11840817_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-38625-4
Online ISBN: 978-3-540-38627-8
eBook Packages: Computer ScienceComputer Science (R0)