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：2020
摘要
Adaptive 熱力學 systems -- such as a 生物 organism attempting to gain survival advantage, an autonomous robot performing a functional task, or a motor 蛋白質 transporting intracellular nutrients -- can improve their performance by effectively modeling the regularities and 隨機ity in their environments. Analogously, but in a purely 計算 realm, 機器學習 algorithms seek to estimate models that capture predictable structure and identify irrelevant noise in training data by optimizing performance measures, such as a model's log-likelihood of having generated the data. Is there a sense in which these 計算 models are physically preferred? For adaptive physical systems we introduce the organizing principle that 熱力學 work is the most relevant performance measure of advantageously modeling an environment. Specifically
※ 此為已發表論文，全文需透過期刊付費取得