---

為何要“深”？
pluskid的博客 Deep Learning and Shallow Learning

Bengio Y. Learning deep architectures for AI. Foundations and trends? in Machine Learning, 2009

---

Deeper is Better?

---

模型有更多的參數會有更好的結果，這是毋庸置疑的。

深瘦的模型會比淺胖的模型有更好的表達能力。

---

Universality Theorem

---

雖然理論上單層網絡可以表達任意的函數，但是實際上更深的結構在表達函數的能力更出色。

細節見 A visual proof that neural nets can compute any function

---

Do Deep Nets Really Need To Be Deep? (by Rich Caruana)

---

更多細節見 Rich Caruana

“Do Deep Nets Really Need to be Deep?”閱讀筆記

---

參考文獻

---

Home: http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML17.html

A visual proof that neural nets can compute any function

Rich Caruana
Deep Learning: Theoretical Motivations (Yoshua Bengio)
Connections between physics and deep learning

Why Deep Learning Works: Perspectives from Theoretical
Chemistry

總結

以上是生活随笔為你收集整理的李宏毅机器学习课程11~~~为何要深？的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。