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：2020-02-23
摘要
Human learners acquire complex interconnected 網絡s of relational knowledge. The capacity for such learning naturally depends on two factors: the architecture (or 資訊al structure) of the knowledge 網絡 itself and the architecture of the 計算 unit—the 大腦—that encodes and processes the 資訊. That is, learning is reliant on integrated 網絡 architectures at two levels: the epistemic and the 計算, or the conceptual and the 神經. Motivated by a wish to understand conventional human knowledge, here, we discuss emerging work assessing 網絡 con- straints on the learnability of relational knowledge, and theories from 統計 physics that instantiate the principles of 熱力學s and 資訊 theory to offer an explanatory model for such constraints. We then highlight similarities between those constraints on the learnability of relat
※ 此為已發表論文，全文需透過期刊付費取得