Performance modelling and optimisation of RF circuits using support vector machines
Performance modelling and optimisation of RF circuits using support vector machines
The paper presents a novel approach to efficient performance modelling and optimisation which can be applied to automatic synthesis of circuit-level radio frequency (RF) analogue circuits. Support vector machines regression models are used to construct automatically general performance models for RF circuits which lend themselves naturally to pattern-search optimisation by exploring the design space. Experiments show that the approach can provide accurate and extremely fast performance estimation.
317-321
Ren, Xianqiang
c7f83e76-c48c-4690-86e3-f5fddb5e2198
Kazmierski, Tom
a97d7958-40c3-413f-924d-84545216092a
2007
Ren, Xianqiang
c7f83e76-c48c-4690-86e3-f5fddb5e2198
Kazmierski, Tom
a97d7958-40c3-413f-924d-84545216092a
Ren, Xianqiang and Kazmierski, Tom
(2007)
Performance modelling and optimisation of RF circuits using support vector machines.
IEEE International Mixed design conference (MIXDES), Ciechocinek, Poland.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
The paper presents a novel approach to efficient performance modelling and optimisation which can be applied to automatic synthesis of circuit-level radio frequency (RF) analogue circuits. Support vector machines regression models are used to construct automatically general performance models for RF circuits which lend themselves naturally to pattern-search optimisation by exploring the design space. Experiments show that the approach can provide accurate and extremely fast performance estimation.
This record has no associated files available for download.
More information
Published date: 2007
Additional Information:
Event Dates: 2007.06.21 - 2007.06.23
Venue - Dates:
IEEE International Mixed design conference (MIXDES), Ciechocinek, Poland, 2007-01-01
Organisations:
EEE
Identifiers
Local EPrints ID: 264621
URI: http://eprints.soton.ac.uk/id/eprint/264621
PURE UUID: 9258eb7d-9d23-454e-b17a-52b634822211
Catalogue record
Date deposited: 03 Oct 2007
Last modified: 08 Jan 2022 14:46
Export record
Contributors
Author:
Xianqiang Ren
Author:
Tom Kazmierski
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