April 2020
Intermediate to advanced
816 pages
18h 32m
Chinese
Content preview from 精通機器學習
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
284
|
第十章：以 Keras 介紹人工神經網路
這個演算法非常重要
，
值得再次總結
：
對於每一個訓練實例
，
反向傳播演算法會先進行預
測
（
順向
）
並評量誤差
，
接著反向遍歷每一層
，
來評量各個連結貢獻的誤差
（
反向
），
最
後調整連結權重來降低誤差
（
梯度下降步驟
）。
你一定要將所有隱藏層的連結權重設為隨機值
，
否則訓練就會失敗
。
例
如
，
如果所有權重與偏差的初始值都是零
，
在特定層的所有神經元就會一
模一樣
，
因此反向傳播會用一模一樣的方式影響它們
，
讓它們維持一模一
樣
。
換句話說
，
就算每一層都有上百個神經元
，
模型也會表現得好像每一
層都只有一個神經元
，
它不會太聰明
。
如果你改成將權重設為隨機的初始
值
，
就會
打破平衡
，
讓反向傳播可以訓練多樣化的神經元群體
。
為了讓這個演算法正確運作
，
演算法的作者對
MLP
的結構做了一項重大的改變
：
將步階
函數換成
logistic（sigmoid）
函數
，σ(z) = 1 / (1 + exp(–z))。
這是重大的改變
，
因為步階函
數只有平坦的線段
，
因此沒有梯度可以使用
（
梯度下降無法在平面上移動
），
而
logistic
函
數到處都有良好的非零導數
，
可讓梯度下降在每一步都有所進展
。
事實上
，
反向傳播演算
法跟許多其他觸發函數都很搭
，
不是只有
logistic
函數而已
。
此外還有兩種流行的選項
：
雙曲正切函數：tanh(z) = 2σ(2z) – 1
這個觸發函數與
logistic
函數一樣是
S
形的
、
連續的
、
可微的
，
但它的輸出值的範圍是
從
–1
到
1（
而不是
logistic
函數的從
0
到
1）。
這個範圍會在訓練開始的時候
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.