Abstract
A framework presenting a basic conceptual structure used to solve adaptive learning problems in soft real time applications is proposed. Its design consists of two supervised neural networks running simultaneously. One is used for training data and the other is used for testing data. The accuracy of the classification is improved from the previous works by adding outpost vectors generated from prior samples. The testing function is able to test data continuously without being interrupted while the training function is being executed. The framework is designed for a parallel processing and/or a distributed processing environment due to the highly demanded processing power of the repetitive training process of the neural network.
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
Tanprasert, T., Kripruksawan, T.: An approach to control aging rate of neural networks under adaptation to gradually changing context. In: ICONIP 2002, pp. 174–178 (2002)
Tanprasert, T., Kaitikunkajorn, S.: Improving synthesis process of decayed prior sampling technique. In: INTECH 2005, pp. 240–244 (2005)
Burzevski, V., Mohan, C.K.: Hierarchical growing cell structures. In: ICNN 1996, pp. 1658–1663 (1996)
Fritzke, B.: Vector quantization with a growing and splitting elastic network. In: ICANN 1993, pp. 580–585 (1993)
Fritzke, B.: Incremental learning of locally linear mappings. In: ICANN 1995, pp. 217–222 (1995)
Martinez, T.M., Berkovich, S.G., Schulten, K.J.: Neural gas network for vector quantization and its application to time-series prediction. IEEE Transactions on Neural Networks 4(4), 558–569 (1993)
Chalup, S., Hayward, R., Joachi, D.: Rule extraction from artificial neural networks trained on elementary number classification tasks. In: Proceedings of the 9th Australian Conference on Neural Networks, pp. 265–270 (1998)
Craven, M.W., Shavlik, J.W.: Using sampling and queries to extract rules from trained neural networks. In: ICML 1994, pp. 37–45 (1994)
Setiono, R.: Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Computation 9(1), 205–225 (1997)
Sun, R., Peterson, T., Sessions, C.: Beyond simple rule extraction: Acquiring planning knowledge from neural networks. In: WIRN Vietri 2001, pp. 288–300 (2001)
Thrun, S., Mitchell, T.M.: Integrating inductive neural network learning and explanation based learning. In: IJCAI 1993, pp. 930–936 (1993)
Towell, G.G., Shavlik, J.W.: Knowledge based artificial neural networks. Artificial Intelligence 70(1-2), 119–165 (1994)
Mitchell, T., Thrun, S.B.: Learning analytically and inductively. In: Mind Matters: A Tribute to Allen Newell, pp. 85–110 (1996)
Fasconi, P., Gori, M., Maggini, M., Soda, G.: Unified integration of explicit knowledge and learning by example in recurrent networks. IEEE Transactions on Knowledge and Data Engineering 7(2), 340–346 (1995)
Tanprasert, T., Fuangkhon, P., Tanprasert, C.: An improved technique for retraining neural networks in adaptive environment. In: INTECH 2008, pp. 77–80 (2008)
Polikar, R., Udpa, L., Udpa, S.S., Honavar, V.: Learn++: An incremental learning algorithm for supervised neural networks. IEEE Transactions on Systems, Man, and Cybernetics 31(4), 497–508 (2001)
Tanprasert, T., Tanprasert, C., Lursinsap, C.: Contour preserving classification for maximal reliability. In: IJCNN 1998, pp. 1125–1130 (1998)
Fuangkhon, P., Tanprasert, T.: An incremental learning algorithm for supervised neural network with contour preserving classification. In: ECTI-CON 2009, pp. 470–473 (2009)
Fuangkhon, P., Tanprasert, T.: An adaptive learning algorithm for supervised neural network with contour preserving classification. In: Deng, H., Wang, L., Wang, F.L., Lei, J. (eds.) Artificial Intelligence and Computational Intelligence. LNCS (LNAI), vol. 5855, pp. 389–398. Springer, Heidelberg (2009)
Calvert, D., Guan, J.: Distributed artificial neural network architectures. In: HPCS 2005, pp. 2–10 (2005)
Seiffert, U.: Artificial neural networks on massively parallel computer hardware. In: ESANN 2002, pp. 319–330 (2002)
Yang, B., Wang, Y., Su, X.: Research and design of distributed training algorithm for neural networks. In: ICMLC 2005, pp. 4044–4049 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fuangkhon, P., Tanprasert, T. (2010). A Dual Network Adaptive Learning Algorithm for Supervised Neural Network with Contour Preserving Classification for Soft Real Time Applications. In: Graña Romay, M., Corchado, E., Garcia Sebastian, M.T. (eds) Hybrid Artificial Intelligence Systems. HAIS 2010. Lecture Notes in Computer Science(), vol 6076. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13769-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-13769-3_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13768-6
Online ISBN: 978-3-642-13769-3
eBook Packages: Computer ScienceComputer Science (R0)