DocumentCode :
1563417
Title :
Multi-objective Adaptive Scheme for Analog Circuit Design Based on Two-layer Genetic Programming
Author :
Wang, Feng ; Li, Yuanxiang
Author_Institution :
Dept. of Comput. Sci. & Technol., Wuhan Univ.
Volume :
1
fYear :
2005
Firstpage :
274
Lastpage :
278
Abstract :
Analog circuits are very important in many high-speed applications. Since the size of analog circuit is becoming larger and more complex, the design is becoming more and more difficult. In this paper, a novel design approach which uses a divide-and-conquer method to evolve the analog circuits is proposed, and a multi-objective adaptive scheme is presented at the same time. The fitness function can be integrated into a vector and the circuit can be evolved more practically than before by this multi-objective adaptive scheme. The experimental results on the designs of the voltage amplifier and the low-pass filter show that this algorithm is efficient
Keywords :
circuit CAD; divide and conquer methods; genetic algorithms; low-pass filters; analog circuit design; divide-and-conquer method; low-pass filter; multi-objective adaptive scheme; two-layer genetic programming; voltage amplifier; Analog circuits; Application software; Circuit synthesis; Circuit topology; Computer science; Electronic mail; Evolutionary computation; Genetic programming; Joining processes; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
Type :
conf
DOI :
10.1109/ICNNB.2005.1614614
Filename :
1614614
Link To Document :
بازگشت