Title :
The use of trapezoidal function in a linguistic fuzzy relational neural network for speech recognition
Author :
Reyes-Garcia, Carlos A. ; Bandler, Wyllis
Author_Institution :
Dept. of Comput. Sci., Florida State Univ., Tallahassee, FL, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Describes the use of trapezoidal functions as part of the implementation of a fuzzy relational neural network model. In the model, the input features are represented by their respective fuzzy membership values to linguistic properties. The membership values are calculated with trapezoidal functions. The weights of the connections between input and output nodes are described in terms of their fuzzy relations. The output values during training are obtained with the max-min composition, and are given in terms of fuzzy class membership values. The learning algorithm, used is a modified version of the gradient descent backpropagation algorithm. The classification of unknown patterns is made with the relational square product. The system is tested on a speech recognition problem
Keywords :
backpropagation; fuzzy neural nets; pattern classification; speech recognition; fuzzy membership values; gradient descent backpropagation algorithm; learning algorithm; linguistic fuzzy relational neural network; max-min composition; relational square product; speech recognition; trapezoidal function; Computer science; Fuzzy neural networks; Fuzzy set theory; Fuzzy sets; Fuzzy systems; Intelligent networks; Neural networks; Pattern classification; Speech recognition; System testing;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374995
