DocumentCode :
787219
Title :
Analog VLSI neural networks: implementation issues and examples in optimization and supervised learning
Author :
Eberhardt, Silvio P. ; Tawel, Raoul ; Brown, Timothy X. ; Daud, Taher ; Thakoor, Anilkumar P.
Author_Institution :
California Inst. of Technol., Pasadena, CA, USA
Volume :
39
Issue :
6
fYear :
1992
fDate :
12/1/1992 12:00:00 AM
Firstpage :
552
Lastpage :
564
Abstract :
Time-critical neural network applications that require fully parallel hardware implementations for maximal throughput are considered. The rich array of technologies that are being pursued is surveyed, and the analog CMOS VLSI medium approach is focused on. This medium is messy in that limited dynamic range, offset voltages, and noise sources all reduce precision. The authors examine how neural networks can be directly implemented in analog VLSI, giving examples of approaches that have been pursued to date. Two important application areas are highlighted: optimization, because neural hardware may offer a speed advantage of orders of magnitude over other methods; and supervised learning, because of the widespread use and generality of gradient-descent learning algorithms as applied to feedforward networks
Keywords :
VLSI; electronic engineering computing; learning (artificial intelligence); neural nets; optimisation; CMOS VLSI; analog VLSI neural networks; dynamic range; feedforward networks; gradient-descent learning algorithms; noise sources; offset voltages; optimization; supervised learning; time-critical neural nets; CMOS technology; Dynamic range; Neural network hardware; Neural networks; Noise reduction; Optimization methods; Throughput; Time factors; Very large scale integration; Voltage;
fLanguage :
English
Journal_Title :
Industrial Electronics, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0046
Type :
jour
DOI :
10.1109/41.170975
Filename :
170975
Link To Document :
بازگشت