首页 > 科技 > 计算机 > 计算机科学

深度学习：原理与应用实践

作译者：张重生

出版时间：2016-12 千字数：259 版次：01-01 页数：232

开本：16开装帧： I S B N ：9787121304132

换版：

纸质书定价：￥48.0

库存:有

分享到：

共有图书评论0条【查看评论摘要】

看了又看

{{data.bookName}}

￥{{data.price}}

内容简介

前言

上架建议

作者简介

编辑推荐

音视频专区

目 录
深度学习基础篇
第1 章 绪论 ·································································································· 2
1.1 引言 ······································································································· 2
1.1.1 Google 的深度学习成果 ···························································· 2
1.1.2 Microsoft 的深度学习成果························································· 3
1.1.3 国内公司的深度学习成果 ························································· 3
1.2 深度学习技术的发展历程 ···································································· 4
1.3 深度学习的应用领域 ············································································ 6
1.3.1 图像识别领域 ············································································· 6
1.3.2 语音识别领域 ············································································· 6
1.3.3 自然语言理解领域 ····································································· 7
1.4 如何开展深度学习的研究和应用开发 ················································· 7
本章参考文献 ······························································································ 11
第2 章 国内外深度学习技术研发现状及其产业化趋势 ······························· 13
2.1 Google 在深度学习领域的研发现状 ·················································· 13
2.1.1 深度学习在Google 的应用 ······················································ 13
2.1.2 Google 的TensorFlow 深度学习平台 ······································ 14
2.1.3 Google 的深度学习芯片TPU ·················································· 15
2.2 Facebook 在深度学习领域的研发现状 ·············································· 15
2.2.1 Torchnet ···················································································· 15
2.2.2 DeepText ··················································································· 16
2.3 百度在深度学习领域的研发现状 ······················································· 17
2.3.1 光学字符识别 ··········································································· 17
2.3.2 商品图像搜索 ··········································································· 17
2.3.3 在线广告 ·················································································· 18
2.3.4 以图搜图 ·················································································· 18
2.3.5 语音识别 ·················································································· 18
2.3.6 百度开源深度学习平台MXNet 及其改进的深度语音识别系统Warp-CTC ····· 19
2.4 阿里巴巴在深度学习领域的研发现状 ··············································· 19
2.4.1 拍立淘 ······················································································ 19
2.4.2 阿里小蜜——智能客服Messenger ········································· 20
2.5 京东在深度学习领域的研发现状 ······················································· 20
2.6 腾讯在深度学习领域的研发现状 ······················································· 21
2.7 科创型公司（基于深度学习的人脸识别系统） ······························· 22
2.8 深度学习的硬件支撑——NVIDIA GPU ············································ 23
本章参考文献 ······························································································ 24
深度学习理论篇
第3 章 神经网络 ························································································· 30
3.1 神经元的概念 ······················································································ 30
3.2 神经网络 ····························································································· 31
3.2.1 后向传播算法 ··········································································· 32
3.2.2 后向传播算法推导 ··································································· 33
3.3 神经网络算法示例 ·············································································· 36
本章参考文献 ······························································································ 38
第4 章 卷积神经网络 ················································································· 39
4.1 卷积神经网络特性 ················································································ 39
4.1.1 局部连接 ·················································································· 40
4.1.2 权值共享 ·················································································· 41
4.1.3 空间相关下采样 ······································································· 42
4.2 卷积神经网络操作 ·············································································· 42
4.2.1 卷积操作 ·················································································· 42
4.2.2 下采样操作 ·············································································· 44
4.3 卷积神经网络示例：LeNet-5 ····························································· 45
本章参考文献 ······························································································ 48
深度学习工具篇
第5 章 深度学习工具Caffe ········································································ 50
5.1 Caffe 的安装 ························································································ 50
5.1.1 安装依赖包 ·············································································· 51
5.1.2 CUDA 安装 ·············································································· 51
5.1.3 MATLAB 和Python 安装 ························································ 54
5.1.4 OpenCV 安装（可选） ···························································· 59
5.1.5 Intel MKL 或者BLAS 安装 ····················································· 59
5.1.6 Caffe 编译和测试 ····································································· 59
5.1.7 Caffe 安装问题分析 ································································· 62
5.2 Caffe 框架与源代码解析 ···································································· 63
5.2.1 数据层解析 ·············································································· 63
5.2.2 网络层解析 ·············································································· 74
5.2.3 网络结构解析 ··········································································· 92
5.2.4 网络求解解析 ········································································· 104
本章参考文献 ···························································································· 109
第6 章 深度学习工具Pylearn2 ································································ 110
6.1 Pylearn2 的安装 ·················································································· 110
6.1.1 相关依赖安装 ·········································································· 110
6.1.2 安装Pylearn2 ·········································································· 112
6.2 Pylearn2 的使用 ·················································································· 112
本章参考文献 ····························································································· 116
深度学习实践篇（入门与进阶）
第7 章 基于深度学习的手写数字识别 ······················································ 118
7.1 数据介绍 ···························································································· 118
7.1.1 MNIST 数据集 ········································································ 118
7.1.2 提取MNIST 数据集图片 ······················································· 120
7.2 手写字体识别流程 ············································································ 121
7.2.1 模型介绍 ················································································ 121
7.2.2 操作流程 ················································································ 126
7.3 实验结果分析 ···················································································· 127
本章参考文献 ···························································································· 128
第8 章 基于深度学习的图像识别 ····························································· 129
8.1 数据来源 ··························································································· 129
8.1.1 Cifar10 数据集介绍 ································································ 129
8.1.2 Cifar10 数据集格式 ································································ 129
8.2 Cifar10 识别流程 ··············································································· 130
8.2.1 模型介绍 ················································································ 130
8.2.2 操作流程 ················································································ 136
8.3 实验结果分析 ······················································································ 139
本章参考文献 ···························································································· 140
第9 章 基于深度学习的物体图像识别 ······················································ 141
9.1 数据来源 ··························································································· 141
9.1.1 Caltech101 数据集 ·································································· 141
9.1.2 Caltech101 数据集处理 ·························································· 142
9.2 物体图像识别流程 ············································································ 143
9.2.1 模型介绍 ················································································ 143
9.2.2 操作流程 ················································································ 144
9.3 实验结果分析 ···················································································· 150
本章参考文献 ···························································································· 151
第10 章 基于深度学习的人脸识别 ··························································· 152
10.1 数据来源 ························································································· 152
10.1.1 AT＆T Facedatabase 数据库 ·················································· 152
10.1.2 数据库处理 ··········································································· 152
10.2 人脸识别流程 ·················································································· 154
10.2.1 模型介绍 ·············································································· 154
10.2.2 操作流程 ·············································································· 155
10.3 实验结果分析 ·················································································· 159
本章参考文献 ···························································································· 160
深度学习实践篇（高级应用）
第11 章 基于深度学习的人脸识别——DeepID 算法 ································ 162
11.1 问题定义与数据来源 ······································································ 162
11.2 算法原理 ·························································································· 163
11.2.1 数据预处理 ··········································································· 163
11.2.2 模型训练策略 ······································································· 164
11.2.3 算法验证和结果评估 ··························································· 164
11.3 人脸识别步骤 ·················································································· 165
11.3.1 数据预处理 ··········································································· 165
11.3.2 深度网络结构模型 ······························································· 168
11.3.3 提取深度特征与人脸验证 ··················································· 171
11.4 实验结果分析 ·················································································· 174
11.4.1 实验数据 ··············································································· 174
11.4.2 实验结果分析 ······································································· 175
本章参考文献 ···························································································· 176
第12 章 基于深度学习的表情识别 ··························································· 177
12.1 表情数据 ························································································· 177
12.1.1 Cohn-Kanade（CK+）数据库 ············································· 177
12.1.2 JAFFE 数据库 ······································································ 178
12.2 算法原理 ························································································· 179
12.3 表情识别步骤 ·················································································· 180
12.3.1 数据预处理 ··········································································· 180
12.3.2 深度神经网络结构模型 ······················································· 181
12.3.3 提取深度特征及分类 ··························································· 182
12.4 实验结果分析 ·················································································· 184
12.4.1 实现细节 ·············································································· 184
12.4.2 实验结果对比 ······································································· 185
本章参考文献 ···························································································· 188
第13 章 基于深度学习的年龄估计 ··························································· 190
13.1 问题定义 ························································································· 190
13.2 年龄估计算法 ·················································································· 190
13.2.1 数据预处理 ··········································································· 190
13.2.2 提取深度特征 ······································································· 192
13.2.3 提取LBP 特征 ····································································· 196
13.2.4 训练回归模型 ······································································· 196
13.3 实验结果分析 ·················································································· 199
本章参考文献 ···························································································· 199
第14 章 基于深度学习的人脸关键点检测 ················································ 200
14.1 问题定义和数据来源 ······································································ 200
14.2 基于深度学习的人脸关键点检测的步骤 ······································· 201
14.2.1 数据预处理 ··········································································· 201
14.2.2 训练深度学习网络模型 ······················································· 206
14.2.3 预测和处理关键点坐标 ······················································· 207
本章参考文献 ···························································································· 212
深度学习总结与展望篇
第15 章 总结与展望 ················································································· 214
15.1 深度学习领域当前的主流技术及其应用领域 ······························· 214
15.1.1 图像识别 ·············································································· 214
15.1.2 语音识别与自然语言理解 ··················································· 215
15.2 深度学习的缺陷 ·············································································· 215
15.2.1 深度学习在硬件方面的门槛较高 ········································ 215
15.2.2 深度学习在软件安装与配置方面的门槛较高 ···················· 216
15.2.3 深度学习最重要的问题在于需要海量的有标注的数据作为支撑 ··· 216
15.2.4 深度学习的最后阶段竟然变成枯燥、机械、及其耗时的调参工作 ··· 217
15.2.5 深度学习不适用于数据量较小的数据 ································ 218
15.2.6 深度学习目前主要用于图像、声音的识别和自然语言的理解 ····· 218
15.2.7 研究人员从事深度学习研究的困境 ···································· 219
15.3 展望 ································································································· 220
本章参考文献 ···························································································· 220

序言1
如今，深度学习是国际上非常活跃、非常多产的研究领域，它被广泛应用于计算机视觉、图像分析、语音识别和自然语言处理等诸多领域。在多个领域上，深度神经网络已大幅超越了已有算法的性能。
本书是深度学习领域的一本力作。它对深度神经网络尤其是卷积神经网络进行介绍，且注重深度学习的实际应用。而且，本书还对深度学习研发现状进行总结和阐述，包括Google 和Facebook。本书通过示例的方式详解深度学习的具体应用，包括手写数字识别，物体识别，及以人为中心的计算（包括人脸识别、人脸表情识别、年龄估计、人脸关键点定位等）。本书也介绍了深度学习Caffe 和Pylearn2 两个平台，并给出具体示例，介绍如何使用。
本书的所有实验均可重现，对初学者、研究生和工程师有重要参考价值，能够帮助读者掌握深度学习的实战技能。我在访问河南大学期间与本书作者相识。作者和他的学生为本书的出版投入了1 年多的时间，付出了巨大的心血。我相信，本书将会被中国科技界所认可。
Ioannis Pitas
IEEE Fellow
亚里士多德

序言2
深度学习是当前最炙手可热的研究领域，可是缺乏一本系统深入的著作。今天，这本书来了！
本书是目前国内为数不多的深度学习原著之一，更是最接地气的、同时兼顾深度学习理论与应用开发实践的深度学习著作。本书面向深度学习领域的研究人员、工程师、爱好者，能够帮助人们把握国内外深度学习的研究现状和产业化趋势，快速理解深度学习的基础理论，牢固掌握深度学习应用开发的实用技术。无论是本书的深度学习理论介绍还是应用开发实例详解，作者都采用实例驱动的方式，使得抽象的理论变得容易理解、难懂的图像处理与模式识别问题变得具体、落地。 尤其难能可贵的是，本书还对深度学习平台Caffe 的源代码进行了精彩解析。
本书的10 余个实验都经过作者的反复验证，只需按照书中的相关步骤进行实验，读者就可以重现相关的实验结果。通过本书的学习，读者不但能掌握深度学习相关的基础理论，更能切实掌握深度学习的应用开发技能。因此，对于有意从事深度学习研究与应用实践的研究人员、工程师、爱好者，本书是首选之作。
教授
中国信息协会大数据分会副会长
中国最畅销的《云计算》书籍作者

查看更多 > 图书评论

暂无评论

发表图书评论

评论标题：
评论内容：
验证码：: 看不清楚
点击刷新
: 您还没有登录，请登录后再评论。
点击“登录”

购买过本书的顾客还买过

{{data.bookName}}

￥{{data.price}}