---

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(shù)會(huì)有更好的結(jié)果，這是毋庸置疑的。

深瘦的模型會(huì)比淺胖的模型有更好的表達(dá)能力。

---

Universality Theorem

---

雖然理論上單層網(wǎng)絡(luò)可以表達(dá)任意的函數(shù)，但是實(shí)際上更深的結(jié)構(gòu)在表達(dá)函數(shù)的能力更出色。

細(xì)節(jié)見(jiàn) A visual proof that neural nets can compute any function

---

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

---

更多細(xì)節(jié)見(jiàn) Rich Caruana

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

---

參考文獻(xiàn)

---

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(jié)

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?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。