Abstract
A new variant of the back propagation (BP) [1,2] algorithm is proposed in this paper. The BP algorithm is widely used to tune the parameters of multi-layered neural networks and hybrid neural fuzzy systems [3]. Most applications of the BP algorithm are based on the negative gradient descent approach (NGD-BP) [2]. However, NGD-BP may not be suitable for use in neural fuzzy systems due to the poor interpretations of its error signals and over-reliance on prior knowledge of the node functions (i.e. the aggregation and activation functions of individual nodes). In neural fuzzy systems such as the POPFNN [4], the node functions are defined by the inference scheme adopted. This results in the NGD-BP algorithm being overly dependent on the gradient definition defined by the inference engine. That is, a set of customized learning equations is required for a given inference scheme. Hence, a change of the inference scheme requires a re-computation of the back propagation learning equations. This makes the neural fuzzy structure and learning highly dependent on the type of fuzzy inference engine employed. In contrast, the proposed BackPOLE algorithm generates intuitive error signals using a set of pre-defined objectives and is resilient to the change of inference schemes. This is highly desirable since the parameter-learning phase [2] of neural fuzzy systems can then be generalized and be independent of the fuzzy inference scheme. The BackPOLE algorithm has been implemented in a new neural fuzzy architecture named GenSoFNN [5] to demonstrate its effectiveness.
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
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In Rumelhart, D.E., McClelland, J.L. et al. eds. Parallel Distributed Processing, vol. 1, chap. 8, Cambridge, MA: MIT Press (1986)
Lin, C.T., Lee, C.S.G.: Neural Fuzzy Systems-A Neuro-Fuzzy Synergism to Intelligent Systems. Englewood Cliffs, NJ: Prentice Hall (1996)
Nauck, D., Klawonn, F., Kruse, R.: Foundations of Neuro-Fuzzy Systems. Chichester, England; New York: John Wiley (1997)
Quek, C., Zhou, R.W.: POPFNN: A Pseudo Outer-Product Based Fuzzy Neural Network. Neural Networks (1996) 9(9): 1569–1581
Tung, W.L.: A Generalized Platform for Fuzzy Neural Network. Technical Report, ISL-TR-01/01, School of Computer Engineering, Nanyang Technological University, Singapore (2001)
Lin, C.J., Lin, C.T.: An ART-Based Fuzzy Adaptive Learning Control Network. IEEE Trans. Fuzzy Systs. (1997) 5(4): 477–496
Quek, C., Tung, W.L.: A Novel Approach to the Derivation of Fuzzy Membership Functions Using the Falcon-MART Architecture. Pattern Recog. Letters (2001) 22(9): 941–958
Zadeh, L.A.: Calculus of fuzzy restrictions. Fuzzy sets and Their Applications to Cognitive and Decision Processes; New York: Academic 1–39 (1975)
Tung, W.L., Quek, C.: Derivation of GenSoFNN-CRI(S) from CRI-based Fuzzy System. Technical Report, ISL-TR-04/01, School of Computer Engineering, Nanyang Technological University, Singapore (2001)
Turksen, I.B., Zhong, Z.: An approximate analogical reasoning scheme based on similarity measures and interval valued fuzzy sets. Fuzzy Sets and Syst. (1990) 34: 323–346
Fisher, R. A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7 (1936) Part II: 179–188
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tung, W.L., Quek, C. (2002). BackPOLE: Back Propagation Based on Objective Learning Errors. In: Ishizuka, M., Sattar, A. (eds) PRICAI 2002: Trends in Artificial Intelligence. PRICAI 2002. Lecture Notes in Computer Science(), vol 2417. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45683-X_30
Download citation
DOI: https://doi.org/10.1007/3-540-45683-X_30
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44038-3
Online ISBN: 978-3-540-45683-4
eBook Packages: Springer Book Archive