Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/73160
Title: Learning algorithm with Gaussian membership function for Fuzzy RBF neural networks
Authors: Benítez-Díaz, Domingo 
García Quesada, Jesús 
UNESCO Clasification: 120304 Inteligencia artificial
Issue Date: 1995
Journal: Lecture Notes in Computer Science 
Conference: International Workshop on Artificial Neural Networks 
Abstract: In this paper a new learning algorithm for Fuzzy Radial Basis Function Neural Networks is presented which is characterized by its fully-supervising, self-organizing and fuzzy properties, with an associated computational cost that is fewer than other algorithms. II is intended for pattern classification tasks, and is capable of automatically configuring the Fuzzy RBF network. The methodology shown here is bused on the self-determination of network architecture and the self-recruitment of nodes with a gaussian type of activation function. i.e. the center and covariance matrices of the activation functions together with the number of tuned and output nodes. This approach consists in a mix of the ''Thresholding in Features Spaces'' techniques rind the updating strategies of the ''Fuzzy Kohonen Clustering Networks'' introducing a Gaussian Membership function. Its properties are the same as those of the traditional membership function used in Furry c-Means clustering algorithms, but with the membership function proposed here it lets a nearer relationship exist between learning algorithm and network architecture. Data from a real image and the results given by the algorithm ore used to illustrate this method.
URI: http://hdl.handle.net/10553/73160
ISBN: 978-3-540-59497-0
ISSN: 0302-9743
DOI: 10.1007/3-540-59497-3_219
Source: Mira J., Sandoval F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, [ISSN 0302-9743], v. 930, p. 527-534. Springer, Berlin, Heidelberg. (1995)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

81
checked on May 10, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.