Abstract
A new approach is proposed to fit complex nonlinear function by using BRB system in this paper. BRB system is a knowledge-based system instead of a black box, but its parameters can be trained with an optimization framework. Therefore, it combines the advantage of the knowledge-based method and data-driven method, so it can not only overcome the inaccuracy of expert knowledge but also overcome the overfitting problem of data-driven method. An experiment is implemented to compare the performance of BRB system and neural network when fitting a nonlinear system, and the results indicate that BRB system performs much better than neural network when training data is insufficient.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ye, H., Yang, L., Liu, X.: Optimizing weight and threshold of BP neural network using SFLA: applications to nonlinear function fitting. In: International Conference on Emerging Intelligent Data & Web Technologies. pp. 211–214. IEEE, (2013)
Kay, H., Rineer, B., Kuiper, B.: Semi-quantitative system identification. Artif. Intell. 119(1), 103–140 (2000)
Dietterich, T.: Overfitting and undercomputing in machine learning. ACM Comput. Surv. 27(3), 326–327 (1995)
Yang, J.B., Liu, J., Wang, J., Sii, H.S., Wang, H.W.: A belief rule-base inference methodology using the evidential reasoning approach–RIMER. IEEE Trans. Syst. Man Cybernet. Part A 36(2), 266–285 (2006)
Yang, J.B., Liu, J., Xu, D.L., Wang, J., Wang, H.W.: Optimization models for training belief rule based systems. IEEE Trans. Syst. Man Cybernet–Part A 37(4), 569–585 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tang, X., Xiao, M., Hu, B., Gao, C. (2020). Fitting Complex Nonlinear Function with Belief Rule Base. In: Jain, V., Patnaik, S., Popențiu Vlădicescu, F., Sethi, I. (eds) Recent Trends in Intelligent Computing, Communication and Devices. Advances in Intelligent Systems and Computing, vol 1006. Springer, Singapore. https://doi.org/10.1007/978-981-13-9406-5_19
Download citation
DOI: https://doi.org/10.1007/978-981-13-9406-5_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9405-8
Online ISBN: 978-981-13-9406-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)