hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.2001.02.02

An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture

Bojan Novak

Puni tekst: engleski, pdf (374 KB) str. 113-122 preuzimanja: 273* citiraj
APA 6th Edition
Novak, B. (2001). An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture. Journal of computing and information technology, 9 (2), 113-122. https://doi.org/10.2498/cit.2001.02.02
MLA 8th Edition
Novak, Bojan. "An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture." Journal of computing and information technology, vol. 9, br. 2, 2001, str. 113-122. https://doi.org/10.2498/cit.2001.02.02. Citirano 19.02.2020.
Chicago 17th Edition
Novak, Bojan. "An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture." Journal of computing and information technology 9, br. 2 (2001): 113-122. https://doi.org/10.2498/cit.2001.02.02
Harvard
Novak, B. (2001). 'An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture', Journal of computing and information technology, 9(2), str. 113-122. https://doi.org/10.2498/cit.2001.02.02
Vancouver
Novak B. An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture. Journal of computing and information technology [Internet]. 2001 [pristupljeno 19.02.2020.];9(2):113-122. https://doi.org/10.2498/cit.2001.02.02
IEEE
B. Novak, "An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture", Journal of computing and information technology, vol.9, br. 2, str. 113-122, 2001. [Online]. https://doi.org/10.2498/cit.2001.02.02

Sažetak
The fusion of artificial neural networks with soft computing enables to construct learning machines that are superior compared to classical artificial neural networks, because knowledge can be extracted and explained in the form of simple rules. An efficient method for selecting the optimal structure of a fuzzy neural network architecture is developed. The Vapnik Chervonenkis (VC) dimension is introduced as a measure of the capacity of the learning machine. A prediction of the expected error on the yet unseen examples is estimated with the help of the VC dimension. The structural risk minimization principle is introduced for constructing the optimal architecture with the lowest expected error for the small data sets. A comparison between fuzzy neural network and the neural network ARX model is presented.

Hrčak ID: 44812

URI
https://hrcak.srce.hr/44812

Posjeta: 420 *