DocumentCode
2617632
Title
Obtaining high precision operation from nonideal neural networks
Author
Sculley, Terry L. ; Brooke, Martin A.
Author_Institution
Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
fYear
1990
fDate
1-3 May 1990
Firstpage
1847
Abstract
Several potential neural architectures for an A/D converter are examined, and the level of nonidealities that can be tolerated by the network components without inhibiting high-precision operation through training is discussed. Behavioral-level simulations on sample converter networks with modeled nonidealities revealed a strong interrelationship between the network architectures and their tolerance to nonidealities
Keywords
analogue-digital conversion; learning systems; neural nets; A/D converter; behavioural-level simulations; high precision operation; modeled nonidealities; network components; neural architectures; nonideal neural networks; sample converter networks; training; Circuit stability; Computational modeling; Computer architecture; Computer networks; Feedback circuits; Integrated circuit interconnections; Multilayer perceptrons; Neural networks; Pipelines; Telephony;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location
New Orleans, LA
Type
conf
DOI
10.1109/ISCAS.1990.112018
Filename
112018
Link To Document