Skip to Content
精通特征工程
book

精通特征工程

by Alice Zheng, Amanda Casari
April 2019
Intermediate to advanced
172 pages
4h 39m
Chinese
Posts & Telecom Press
Content preview from 精通特征工程
124
8
局部响应归一化在相邻核之间引起竞争
顾名思义,局部响应归一化将某个值除以它的邻居组合,公式如下:
()
2
neighborhoodof
kk
k
y
xc x
β
α
=+
其中,
x
k
是第
k
个核的输出,
y
k
相对于邻域中其他核的归一化响应。对于每个输出位
置,归一化是分别进行的;也就是说,对每个输出位置
(
i
,
j
)
,我们都通过附近的卷积
核输出进行归一化。注意,这不同于通过图像邻域或输出位置进行的归一化。核邻域
的大小
c
α
β
都是通过图像验证集调优的超参数。
8.3.5
 池化层
池化层将多个输入组合成一个输出。当卷积滤波器在图像上移动时,每处理一个邻域都会
生成一个输出。池化强制一个局部图像邻域生成一个值,而不是多个值。这可以减少深度
学习网络中间层的输出数量,从而有效降低网络在训练数据时出现过拟合的概率。
有多种方法可以池化输入:求平均值、求和(或计算广义的范数)或取最大值。池化可以
沿着图像或中间输出层移动进行。
AlexNet
使用重叠的最大值池化,在图像中以两个像素
(或输出)的步长进行移动,在
3
个邻居之间进行池化,见图
8-13
最大值池化
输出
输入
步长=2
宽度=3
8-13:最大值池化使用非线性下采样在每个子区域输出非重叠矩形的最大数量
8.3.6
 
AlexNet
的结构
总体来说,
AlexNet
包括
5
个卷积层、
2
个响应归一化层、
3
个最大值池化层和
2
个全连接层。
加上最终的分类输出层,模型中一共有
13
个神经网络层,形成了
8
个层组,详见图
8-14
自动特征生成:图像特征提取和深度学习
125 ...
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

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’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.
Head of Cybersecurity
QuotationMarkI 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.
Field Engineer
QuotationMarkI’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.
Data Platform Tech Lead
QuotationMarkI'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.
Mark W.
Embedded Software Engineer

You might also like

精通機器學習

精通機器學習

Aurélien Géron

Publisher Resources

ISBN: 9787115509680