Skip to Content
深度学习:核心原理与案例分析
book

深度学习:核心原理与案例分析

by Posts & Telecom Press, Ahmed Menshawy
May 2024
Intermediate to advanced
389 pages
6h 49m
Chinese
Packt Publishing
Content preview from 深度学习:核心原理与案例分析

第7章 卷积神经网络

在数据科学中,卷积神经网络(Convolutional NeuralNetwork,CNN)是一类特定的深度学习架构,它利用卷积运算来挖掘输入图像中的相关的可解释特征。CNN层之间像前馈神经网络一样互相连接,同时它利用卷积操作来模拟人类识别物体时大脑的工作原理。单个皮层神经元只对空间中某个受限区域的刺激做出反应,这称为感受野。特别地,生物医学成像曾一度是一个很有挑战性的问题,但在本章中,读者将看到如何利用CNN来发掘图像中的模式。

本章将包含以下主题。

  • 卷积运算。
  • 动机。
  • CNN的不同层。
  • CNN基础示例——MNIST手写数字分类。

CNN在计算机视觉领域里广泛应用,并且它们表现得比前人所使用的大多数传统计算机视觉技术要出色。CNN将著名的卷积运算和神经网络结合在一起,因此叫作卷积神经网络。因此,在深入讨论CNN的神经网络部分之前,本书将先介绍卷积运算并看看它是怎么工作的。

卷积运算的主要目的是从图像中提取信息或特征。任何图像都可以看作一个数值矩阵,而矩阵中一组特定的数值可以构成一个特征。卷积运算的目的是扫描这个矩阵,并尝试为图像挖掘相关的或可解释特征。例如,考虑一个5×5的图像,它的对应灰度(或者说像素值),用0和1来表示,如图7.1所示。

..\19-0460 图\7-1.tif

图7.1 5×5的像素值矩阵

再考虑图7.2所示的3×3的矩阵。

图7.2 3×3的像素值矩阵

如图7.3(a)~(i)所示,可以用3×3的矩阵对5×5的图像进行卷积。

  

  

  

  

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

scikit-learn机器学习(第2版)

scikit-learn机器学习(第2版)

Posts & Telecom Press, Gavin Hackeling
自然语言处理与计算语言学

自然语言处理与计算语言学

Posts & Telecom Press, Bhargav Srinivasa-Desikan
Python机器学习案例精解

Python机器学习案例精解

Posts & Telecom Press, Yuxi (Hayden) Liu
Python数据分析(第2版)

Python数据分析(第2版)

Posts & Telecom Press, Armando Fandango

Publisher Resources

ISBN: 9781836201212