累積探索を用いた進化論的手法による関数発見システム

摘要

近年，遺伝的アルゴリズム（GA）と遺伝的プログラミrnング（GP）を使用するさまざまな問題解決システムが提rn案されている。GAが主にスケジューリング問題，最適配rn置問題などの組み合わせ最適化問題や，パラメータ最適化rnや関数最適化問題などの数値最適化問題に対する有効な最rn適化手法として利用されるのに対し，GPは遺伝子を木構rn造で表現し，交叉，突然変異を用いて関数，プログラムのrn自動生成を目的とする。%Recently, a system using the bug-type artificial life was proposed for discovering the function, and has been improved further. This system is one of the extended models of the GA and GP. However, when the observation data is very complicated, the function is occasionally not obtained. In this study, a new concept has been introduced in order that the function search can be applied to the complicated observation data. The function search by the S-System is executed twice or more number of times. This is termed search-accumulation. To confirm the validity of search-accumulation, the Himmelblau function, valley function, and equal-loudness level contours (ISO226) are used as the observation data. Since the distributions of the data are complicated, it is difficult to express them as the function of approximation. By the use of the search-accumulation strategy, the function that is in good agreement with the distribution can be successfully obtained. Thus, the validity of this strategy is confirmed. Search-accumulation is also applicable to GP.