DocumentCode :
787192
Title :
Solving a placement problem by means of an analog neural network
Author :
Kita, Hajime ; Odani, Hideyuki ; Nishikawa, Yoshikazu
Author_Institution :
Dept. of Electr. Eng., Kyoto Univ., Japan
Volume :
39
Issue :
6
fYear :
1992
fDate :
12/1/1992 12:00:00 AM
Firstpage :
543
Lastpage :
551
Abstract :
The effectiveness of the Hopfield model is examined through its application to a circuit block placement problem. The results of computer simulation show that, although the Hopfield model is not effective enough if it is used without sophisticated preexamination of combinatorial problems, it has the ability to yield quite satisfactory solutions when it is endowed with an appropriate form and parameters of the energy function. The meaning of appropriate parameter values yielding good solutions is also investigated theoretically
Keywords :
Hopfield neural nets; circuit layout CAD; Hopfield model; analog neural network; circuit block placement problem; computer simulation; energy function; Analog computers; Application software; Circuits; Computer networks; Computer simulation; Design optimization; Hopfield neural networks; Large scale integration; Neural networks; Neurons;
fLanguage :
English
Journal_Title :
Industrial Electronics, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0046
Type :
jour
DOI :
10.1109/41.170974
Filename :
170974
Link To Document :
بازگشت