Summary
We propose, theorize and implement the Recursive Pattern-based Hybrid Supervised (RPHS) learning algorithm. The algorithm makes use of the concept of pseudo global optimal solutions to evolve a set of neural networks, each of which can solve correctly a subset of patterns. The pattern-based algorithm uses the topology of training and validation data patterns to find a set of pseudo-optima, each learning a subset of patterns. It is therefore well adapted to the pattern set provided. We begin by showing that finding a set of local optimal solutions is theoretically equivalent, and more efficient, to finding a single global optimum in terms of generalization accuracy and training time. We also highlight that, as each local optimum is found by using a decreasing number of samples, the efficiency of the training algorithm is increased. We then compare our algorithm, both theoretically and empirically, with different recursive and subset based algorithms. On average, the RPHS algorithm shows better generalization accuracy, with improvement of up to 60% when compared to traditional methods. Moreover, certain versions of the RPHS algorithm also exhibit shorter training time when compared to other recent algorithms in the same domain. In order to increase the relevance of this paper to practitioners, we have added pseudo code, remarks, parameter and algorithmic considerations where appropriate.
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
Alexander JA, Mozer M (1999) Template-based procedures for neural network interpretation. Neural Netw 12:479–498
Andrews R, Diedrich J, Tickle A (1995) Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl-Based Syst 8(6):373–389
Andrews R, Geva S (1994) Rule extraction from constrained error back propagation MLP. In: Proceedings of 5th Australian conference on neural networks, Brisbane, Quinsland, pp 9–12
Blake CC, Merz C (1998) UCI Repository of Machine Learning Databases. University of California, Irvine, Department of Information and Computer Sciences.
Bologna G (2000) A study on rule extraction from neural network applied to medical databases. In: The 4th European conference on principles and practice of knowledge discovery
Castillo L, González A, Pérez R (2001) Including a simplicity criterion in the selection of the best rule in a genetic algorithm. Fuzzy Sets Syst 120:309–321
Cichocki A, Unbehauen R (1993) Neural networks for optimization and signal processing. Wiley, London
Eiben A, Aarts E, Hee K (1991) Parallel problem solving from nature. Chapter Global convergence of genetic algorithms: a Markov chain analysis, Springer, Berlin Heidelberg New York, p 412
Eiben AE, Smith J (2003) Introduction to evolutionary computing. Natural computing series, Springer, Berlin Heidelberg Newyork
Fu X, Wang L (2001) Rule extraction by genetic algorithms based on a simplified RBF neural network. In: Proceedings congress on evolutionary computation, pp 753–758
Haddadnia J, Ahmadi M, Faez P (2002) A hybrid learning RBF neural network for human face recognition with pseudo Zernike moment invariant. In: IEEE international joint conference on neural network
Hayashi Y, Setiono R, Yoshida K (2000) Learning M of N concepts for medical diagnosis using neural networks. J Adv Comput Intell 4:294–301
Hayward R, Ho-Stuart C, Diedrich J, et al. (1996) RULENEG: extracting rules from trained ANN by stepwise negation. Technical report, Neurocomputing Research Centre Queensland University Technology Brisbane, Old
Hruschka ER, Ebecken N (2000) A clustering genetic algorithm for extracting rules from supervised neural network models in data mining Tasks’. IJCSS 1(1)
Jin Y, Sendhoff B, Koerner E (2005a) Evolutionary multi-objective optimization for simultaneous generation of signal-type and symbol-type representations. In: The third international conference on evolutionary multi-criterion optimization, pp 752–766
Jin Y, Sendhoff B, Korner E (2005b) Evolutionary multiobjective optimization for simultanous generation of signal type and symbol type representation. In: EMO 2005 LNCS, pp 752–766
Keedwell E, Narayanan A, Savic D (1999) Using genetic algorithm to extract rules from trained neural networks. In: Proceedings of the genetic and evolutionary computing conference, pp 793–804
Keedwell E, Narayanan A, Savic D (2000) Creating rules from trained neural networks using genetic algorithms. IJCSS 1(1):30–43
Lu H, Setiono R, Liu H (1995) NeuroRule: a connectionist approach to data mining. In: Proceedings of the 21th conference on very large databases, Zurich, pp 478–489
Markowska-Kaczmar U (2005) The influence of parameters in evolutionary based rule extraction method from neural network. In: Proceedings of 5th international conference on intelligent systems design and applications pp 106–111
Markowska-Kaczmar U, Chumieja M (2004) Discovering the mysteries of neural networks. Int J Hybrid Intell Syst 1(3/4):153–163
Markowska-Kaczmar U, Mularczyk K (2006) GA-based pareto optimization, Vol. 16 of Studies in computational intelligence. Springer, Berlin Heidelberg Newyork
Markowska-Kaczmar U, Trelak W (2005) Fuzzy logic and evolutionary algorithm - two techniques in rule extraction from neural networks. Neurocomputing 63:359–379
Markowska-Kaczmar U, Wnuk-Lipinski P (2004) Rule extraction from neural network by genetic algorithm with pareto optimization. In: Rutkowski L (ed.) Artificial intelligence and soft computing, pp 450–455
Michalewicz Z (1996) Genetic algorithms + Data structures = Evolution programs. Springer, Berlin Heidelberg Newyork
Mitra S, Yoichi H (2000) Neuro-fuzzy rule generation: survey in soft computing framework. IEEE Trans Neural Netw 11(3):748–768
Omidvar O, Van der Smagt P (eds.) (1997) Neural systems for robotics. Academic, New York
Palade V, Neagu DC, Patton RJ (2001) Interpretation of trained neural networks by rule extraction. Fuzzy days 2001, LNC 2206, pp 152–161
Reil T, Husbands P (2002) Evolution of central pattern generators for bipedal walking in a real-time physics environment. IEEE Trans Evol Comput 6(2):159–168
Robert C, Gaudy JF, Limoge A (2002) Electroencephalogram processing using neural network. Clin Neurophysiol 113(5):694–701
Santos R, Nievola J, Freitas A (2000) Extracting comprehensible rules from neural networks via genetic algorithms Symposium on combinations of evolutionary computation and neural network 1:130–139
Setiono R, Leow WK, Zurada J (2002) Extraction of rules from artificial neural networks for nonlinear regression. IEEE Trans Neural Netw 13(3):564–577
Siponen M, Vesanto J, Simula O, Vasara P (2001) An approach to automated interpretation of SOM. In: Proceedings of workshop on self-organizing map 2001 (WSOM2001), pp 89–94
Taha I, Ghosh J (1999) Symbolic interpretation of artificial neural networks. IEEE Trans Knowl Data Eng 11(3):448–463
Thrun SB (1995) Advances in neural information processing systems. MIT, San Mateo, CA
Van der Zwaag B-J (2001) Handwritten digit Recognition: a neural network demo. In: Computational intelligence: theory and applications, Vol. 2206 of Springer LNCS. Dortmund, Germany, pp 762–771
Widrow B, Rumelhart DE, Lehr M (1994) Neural networks: applications in industry, business and science. Commun ACM 37(3):93–105
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ramanathan, K., Guan, S.U. (2008). Recursive Pattern based Hybrid Supervised Training. In: Abraham, A., Grosan, C., Pedrycz, W. (eds) Engineering Evolutionary Intelligent Systems. Studies in Computational Intelligence, vol 82. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75396-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-75396-4_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75395-7
Online ISBN: 978-3-540-75396-4
eBook Packages: EngineeringEngineering (R0)