作成者 |
|
|
|
本文言語 |
|
出版者 |
|
|
発行日 |
|
収録物名 |
|
巻 |
|
号 |
|
開始ページ |
|
終了ページ |
|
出版タイプ |
|
アクセス権 |
|
JaLC DOI |
|
関連DOI |
|
関連URI |
|
関連情報 |
|
概要 |
Genetic Algorithms (GA) are a class of stochastic optimization algorithms based on natural evolution. We have designed "GAP" (Genetic Algorithm Processor), a general-purpose VLSI for GA. It is based o...n Steady-State GA, and achieves better performance by pipeline parallelization than other GA-VLSIs, which are based on conventional generation-based GA. Moreover, GAP introduces "Simplified Tournament Selection" scheme for implementing the selection module. This scheme is proved much simpler, faster, and better in convergence compared to "Roulette Wheel Selection" scheme, which is widely used in other GA-VLSI's.続きを見る
|