Power scalable implementation of artificial neural networks
Power scalable implementation of artificial neural networks
As the use of Artificial Neural Network (ANN) in mobile embedded devices gets more pervasive, power consumption of ANN hardware is becoming a major limiting factor. Although considerable research efforts are now directed towards low-power implementations of ANN, the issue of dynamic power scalability of the implemented design has been largely overlooked. In this paper, we discuss the motivation and basic principles for implementing power scaling in ANN Hardware. With the help of a simple example, we demonstrate how power scaling can be achieved with dynamic pruning techniques.
Modi, Sankalp
28a7f336-f2b6-4a5e-8d9a-7c0ed64194b9
Wilson, Peter
8a65c092-c197-4f43-b8fc-e12977783cb3
Brown, Andrew
5c19e523-65ec-499b-9e7c-91522017d7e0
2005
Modi, Sankalp
28a7f336-f2b6-4a5e-8d9a-7c0ed64194b9
Wilson, Peter
8a65c092-c197-4f43-b8fc-e12977783cb3
Brown, Andrew
5c19e523-65ec-499b-9e7c-91522017d7e0
Modi, Sankalp, Wilson, Peter and Brown, Andrew
(2005)
Power scalable implementation of artificial neural networks.
IEEE International Conference on Electronics, Circuits and Systems (ICECS), Tunisia.
Record type:
Conference or Workshop Item
(Paper)
Abstract
As the use of Artificial Neural Network (ANN) in mobile embedded devices gets more pervasive, power consumption of ANN hardware is becoming a major limiting factor. Although considerable research efforts are now directed towards low-power implementations of ANN, the issue of dynamic power scalability of the implemented design has been largely overlooked. In this paper, we discuss the motivation and basic principles for implementing power scaling in ANN Hardware. With the help of a simple example, we demonstrate how power scaling can be achieved with dynamic pruning techniques.
Text
photo_ready_ICECS.pdf
- Other
More information
Published date: 2005
Additional Information:
Event Dates: December 2005
Venue - Dates:
IEEE International Conference on Electronics, Circuits and Systems (ICECS), Tunisia, 2005-12-01
Organisations:
EEE
Identifiers
Local EPrints ID: 261635
URI: http://eprints.soton.ac.uk/id/eprint/261635
PURE UUID: ef9289e8-4a33-4be4-bf5b-7a75c68102f8
Catalogue record
Date deposited: 09 Dec 2005
Last modified: 14 Mar 2024 06:56
Export record
Contributors
Author:
Sankalp Modi
Author:
Peter Wilson
Author:
Andrew Brown
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics