DocumentCode :
1817920
Title :
On-chip learning in the analog domain with limited precision circuits
Author :
Montalvo, Antonio J. ; Hollis, Paul W. ; Paulos, John J.
Author_Institution :
North Carolina State Univ., Raleigh, NC, USA
Volume :
1
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
196
Abstract :
The precision constraints imposed by gradient descent learning in the analog domain are considered. Previous studies have investigated the precision necessary to perform weight update calculations with weights stored in digital registers. These studies have found that the learning calculations must be performed with at least 12 b of precision while the feedforward precision can be as low as 6 b. In the present work, the effect of offsets when performing calculations in the analog domain is investigated. An alteration to the standard weight perturbation algorithm is proposed. It allows learning with offsets as large as 1 part in 8 b, thus allowing fast on-chip learning with weights stored in dense analog memory
Keywords :
analogue storage; feedforward neural nets; learning (artificial intelligence); neural chips; analog domain; dense analog memory; digital registers; feedforward precision; gradient descent learning; limited precision circuits; on-chip learning; weight perturbation algorithm; weight update; Analog computers; Analog memory; Backpropagation algorithms; Circuits; Clocks; Neural network hardware; Neurons; Quantization; Registers; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.287136
Filename :
287136
Link To Document :
بازگشت