本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：1994
摘要
How does 演化 produce sophisticated emergent computation in systems composed of simple components limited to local interactions? To model such a process, we used a 遺傳 algorithm (GA) to evolve 細胞自動機 to perform a 計算 task requiring globally-coordinated 資訊 processing. On most runs a class of relatively unsophisticated strategies was evolved, but on a subset of runs a number of quite sophisticated strategies was discovered. We analyze the emergent logic underlying these strategies in terms of 資訊 processing performed by "particles" in space-time, and we describe in detail the generational progression of the GA 演化 of these strategies. Our analysis is a preliminary step in understanding the general mechanisms by which sophisticated emergent 計算 capabilities can be automatically produced in decentrali
※ 此為已發表論文，全文需透過期刊付費取得