ESTYLF 2000, X Congreso Español sobre Tecnologías y Lógica Fuzzy, Seville (Spain). 20-22 Septiembre 2000
Summary:
This paper describes the main results concerning a comparative study between simple architectures of trained neural networks using the logistic function as activation function, and the performance of the classic Lukasiewicz operators. The paper shows how those operators can explain trained neural networks. Other fuzzy operators are tested and the results explained. In all cases the results obtained promise an advance in the explanation of trained neural networks using fuzzy logic.
Keywords: Rule extraction, neural networks, fuzzy logic
Publication date: September 2000.
Citation:
Tejedor, P., Sanz-Bobi, M.A., Aproximaciones entre las redes neuronales y los operadores borrosos, ESTYLF 2000, X Congreso Español sobre Tecnologías y Lógica Fuzzy, Seville (Spain). 20-22 September 2000.
IIT-00-011A
Due to copyright restriction we cannot distribute this content on the web. However, using the next form you can contact the authors, which are allowed to redistribute a limited number of copies of it by email. Please, check your spam folder.
Legal notice | Cookies policy | Privacy policy
Calle de Santa Cruz de Marcenado, 26 - 28015 Madrid, Spain - Tel: (+34) 91 542 28 00
We use our own and third-party cookies to improve the functionality of our website and the quality of our service, by analyzing your browsing habits. I accept this site's cookies.
|
|