DocumentCode
1932878
Title
Precision requirements for single-layer feedforward neural networks
Author
Annema, A.J. ; Hoen, K. ; Wallinga, H.
Author_Institution
MESA Res. Inst., Twente Univ., Enschede, Netherlands
fYear
1994
fDate
26-28 Sep 1994
Firstpage
145
Lastpage
151
Abstract
This paper presents a mathematical analysis of the effect of limited precision analog hardware for weight adaptation to be used in on-chip learning feedforward neural networks. Easy-to-read equations and simple worst-case estimations for the maximum tolerable imprecision are presented. As an application of the analysis, a worst-case estimation on the minimum size of the weight storage capacitors is presented
Keywords
analogue multipliers; feedforward neural nets; learning (artificial intelligence); mathematical analysis; neural chips; limited precision analog hardware; mathematical analysis; maximum tolerable imprecision; on-chip learning; precision requirements; single-layer feedforward neural networks; weight adaptation; weight storage capacitors; worst-case estimations; Equations; Feedforward neural networks; Feedforward systems; Mathematical analysis; Network-on-a-chip; Neural network hardware; Neural networks; Neurons; Performance analysis; Signal analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Microelectronics for Neural Networks and Fuzzy Systems, 1994., Proceedings of the Fourth International Conference on
Conference_Location
Turin
Print_ISBN
0-8186-6710-9
Type
conf
DOI
10.1109/ICMNN.1994.593243
Filename
593243
Link To Document