Title :
Neural network learning paradigms involving nonlinear spectral processing
Author :
Ersoy, O.K. ; Hong, D.
Author_Institution :
Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN, USA
Abstract :
Two neural network architectures involving nonlinear spectral transformations are described. The first architecture involves generalization of nonlinear matched-filtering techniques, yielding a network that is very fast in learning and recall as well as highly accurate in classification. The second architecture is hierarchical with a number of stages; after each stage, error detection is carried out, followed by nonlinear spectral transformations when the error measure is above threshold
Keywords :
error detection; filtering and prediction theory; learning systems; matched filters; neural nets; signal processing; classification; error detection; hierarchical architecture; learning paradigms; matched-filtering techniques; neural network architectures; nonlinear spectral processing; recall; Convergence; Costs; Discrete Fourier transforms; Feature extraction; Filtering; Intelligent networks; Matched filters; Neural networks; Neurons; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266794
