An evolutionary neural network approach for module orientation problems

Author

Funabiki, Nobuo ; Kitamichi, Junji ; Nishikawa, Seishi

Author_Institution

Dept. of Inf. & Comput. Sci., Osaka Univ., Japan

Volume

28

Issue

6

fYear

1998

fDate

12/1/1998 12:00:00 AM

Firstpage

849

Lastpage

855

Abstract

A novel neural network approach called “Evolutionary Neural Network (ENN)” is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time

Keywords

computational complexity; evolutionary computation; heuristic programming; neural nets; simulated annealing; NP-complete problem; circuit modules; evolutionary initialization scheme; evolutionary neural network approach; genetic algorithm; heuristic algorithms; high quality VLSI systems; module orientation problems; neuron states; simulations; Circuits; Computational modeling; Genetic algorithms; Heuristic algorithms; NP-complete problem; Neural networks; Neurons; Simulated annealing; Very large scale integration; Wire;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/3477.735394

Filename

735394