A novel non-iterative parameter estimation method for interval type-2 fuzzy neural networks based on a dynamic cost function

Khanesar, Mojtaba Ahmadieh; Hassan, Saima; Cambria, Erik; Kayacan, Erdal

Abstract

Non-iterative methods for parameter estimation for interval type-2 neuro-fuzzy structure are fast to implement, when compared to online methods, and need no –or a few– parameters to be tuned. In this paper, a novel dynamic cost function, which defines a relationship between the current and past errors, is defined. The minimization of the aforementioned cost function results in a decreasing sequence of error which makes the proposed method numerically more stable when compared to least squares-based methods. It is a well-known phenomenon that a matrix inversion may cause problems if the matrix to be inverted is ill-defined i.e. its condition number is far bigger than one. The use of a dynamic relationship between the current and past error adds more degrees of freedom which makes it possible to improve the condition number of the matrix. Comprehensive simulation studies are presented for the prediction of financial data sets. The simulation results shows the superior numerical stability of the proposed method as the mean value of the condition number is smaller. This finding results in more accurate matrix inversion to be done in the two-step matrix inversion.

Citation

Khanesar, M. A., Hassan, S., Cambria, E., & Kayacan, E. (2019). A novel non-iterative parameter estimation method for interval type-2 fuzzy neural networks based on a dynamic cost function.

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: International Conference on Fuzzy Systems (FUZZ -IEEE 2019)
• Start Date: Jun 23, 2019
• End Date: Jun 26, 2019
• Acceptance Date: Mar 7, 2019
• Publication Date: Jun 23, 2019
• Deposit Date: May 10, 2019
• Publicly Available Date: May 10, 2019
• Publisher: Institute of Electrical and Electronics Engineers
• Public URL: https://nottingham-repository.worktribe.com/output/2037598
• Related Public URLs: http://sites.ieee.org/fuzzieee-2019/
• Contract Date: May 10, 2019