DocumentCode :
2412478
Title :
Extraction of piecewise-linear analog circuit models from trained neural networks using hidden neuron clustering
Author :
Doboli, Simona ; Gothoskar, G. ; Doboli, Alex
Author_Institution :
Comput. Sci. Dept., Hofstra Univ., Hempstead, NY, USA
fYear :
2003
fDate :
2003
Firstpage :
1098
Lastpage :
1099
Abstract :
This paper presents a new technique for automatically creating analog circuit models. The method extracts - from trained neural networks-piecewise linear models expressing the linear dependencies between circuit performances and design parameters. The paper illustrates the technique for an OTA circuit for which models for gain and bandwidth were automatically generated. The extracted models have a simple form that accurately fits the sampled points and the behavior of the trained neural networks. These models are useful for fast simulation of systems with non-linear behavior and performances.
Keywords :
active networks; integrated circuit modelling; mixed analogue-digital integrated circuits; neural nets; piecewise linear techniques; OTA circuit; bandwidth; circuit performances; design parameters; gain; hidden neuron clustering; linear dependencies; nonlinear behavior; piecewise-linear analog circuit models; sampled points; trained neural networks; Analog circuits; Neural networks; Neurons; Piecewise linear techniques;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Design, Automation and Test in Europe Conference and Exhibition, 2003
ISSN :
1530-1591
Print_ISBN :
0-7695-1870-2
Type :
conf
DOI :
10.1109/DATE.2003.1253752
Filename :
1253752
Link To Document :
بازگشت