Scheduled System Maintenance:
On April 27th, single article purchases and IEEE account management will be unavailable from 2:00 PM - 4:00 PM ET (18:00 - 20:00 UTC).
We apologize for the inconvenience.
By Topic

Analysis of simulation-driven numerical performance modeling techniques for application to analog circuit optimization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
2 Author(s)
McConaghy, T. ; ESAT-MICAS, Katholieke Univ., Leuven, Belgium ; Gielen, G.

There is promise of efficiency gains in simulator-in-the-loop analog circuit optimization if one uses numerical performance modeling on simulation data to relate design parameters to performance values. However, the choice of modeling approach can impact performance. We analyze and compare these approaches: polynomials, posynomials, genetic programming, feedforward neural networks, boosted feedforward neural networks, multivariate adaptive regression splines, support vector machines, and kriging. Experiments are conducted on a dataset used previously for posynomial modeling, showing the strengths and weaknesses of the different methods in the context of circuit optimization.

Published in:

Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on

Date of Conference:

23-26 May 2005