Title :
Multiplierless neural networks for application to digital video
Author :
Cavanagh, M. ; Jain, V.K.
Author_Institution :
Dept. of Electr. Eng., Univ. of South Florida, Tampa, FL, USA
Abstract :
Advances in artificial neural networks have led to several applications such as in computer-vision, image restoration, speech recognition, and pattern classification. However, for widespread practical use these and many other potential applications require large, high-speed networks implemented in efficient custom hardware. This paper investigates an important issue in the implementation of such networks, namely the avoidance of multipliers. Secondly, it evaluates their application in digital video, specifically in high-performance motion prediction and frame reconstruction. The authors discuss the multilayer perceptron and Hopfield neural networks in particular
Keywords :
Hopfield neural nets; digital communication; image reconstruction; motion estimation; multilayer perceptrons; video signal processing; Hopfield neural networks; artificial neural networks; computer-vision; custom hardware; digital video; frame reconstruction; high-performance motion prediction; image restoration; large high-speed networks; multilayer perceptron; multiplierless neural networks; pattern classification; speech recognition; Application software; Artificial neural networks; Computer networks; High-speed networks; Image reconstruction; Image restoration; Neural network hardware; Neural networks; Pattern classification; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.550611
