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.
452
|
第十四章：使用摺積神經網路來製作深度電腦視覺
AlexNet
也在
C1
和
C3
層的
ReLU
步驟之後立刻使用有競爭性的正規化步驟
，
稱為
局部響
應正規化
（local response normalization，LRN），
它會讓接收最強烈刺激的神經元抑制相鄰
特徵圖的同一個位置的神經元
（
有人已經在生物神經元中發現這種競爭性觸發
）。
這可以
促使不同的特徵圖更加專門化
，
將它們分開
，
並迫使它們探索更廣泛的特徵
，
最終提高類
推能力
。
公式
14-2
是套用
LRN
的做法
。
公式
14-2
局部響應正規化
（LRN）
在這個公式中
：
•
b
i
是在
i
特徵圖的第
u
列
，
第
v
行的神經元的正規化輸出
（
在這個公式中
，
我們只考
慮在這一列這一行的神經元
，
所以沒有寫出
u
和
v）。
•
a
i
是該神經元經歷
ReLU
步驟之後
，
在正規化之前的刺激
。
•
k
、
α
、
β
和
r
是超參數
，
k
稱為
偏差
（
bias
），
r
稱為
深度半徑
（
depth
radius
）。
•
f
n
是特徵圖的數量
。
例如
，
如果
r = 2，
而且神經元有很強的刺激
，
它會抑制在它上面和下面的特徵圖裡面的神
經元的觸發
。
AlexNet
的超參數值是
：r = 2、α = 0.00002、β = 0.75，
且
k = 1。
這個步驟可以用
tf.nn.
local_response_normalization()
函式來實作
（
如果你想要在
Keras
模型裡面使用它
，
可以
將它包在
Lambda
層裡面
）。
AlexNet
有一種稱為
ZF Net（https://homl.info/zfnet）
12
的變體
，
它是
Matthew Zeiler ...
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.