工业人工智能概论

定　　价：56 元

• 作者：韩英华 等
• 出版时间：2020/1/1
• ISBN：9787121381621
• 出 版 社：电子工业出版社

• 中图法分类：F407.4-39 
• 页码：164
• 版次：01
• 开本：16开

内容简介

本书以人工智能技术在工业中的应用为出发点，系统、深入地阐述了工业人工智能的关键技术，并给出了大量的应用案例。全书共 5 章，包括绪论、数据分析与数据挖掘工具、机器学习、深度学习和工业人工智能面临的挑战。本书可作为相关专业的本科生及研究生学习工业人工智能的入门教材，也可作为专业技术人员了解工业人工智能的培训教材和参考书，还可作为对工业人工智能感兴趣的各界人士的普及性读物。

作者介绍

2008.03-2010.12：东北大学秦皇岛分校讲师；2011.01-2016.12：东北大学秦皇岛分校副教授；2017.01-至今：东北大学秦皇岛分校教授；2012年荣获秦皇岛市十大青年风尚人物称号；2013年度河北省"三三三人才工程”第三层次人选；2014年荣获秦皇岛市优秀科技工作者称号

目 录

第 1 章 绪论·····················································································1
1.1 人工智能的内涵及发展····································································1
1.2 工业人工智能的内涵及发展······························································4
1.2.1 工业人工智能的发展背景 ·····························································4
1.2.2 工业人工智能的发展历程 ·····························································6
1.2.3 工业人工智能与传统人工智能的区别················································7
1.3 工业人工智能的算法功能和典型应用··················································8
1.4 工业人工智能的知识体系································································11
1.5 工业人工智能的关键技术································································12
第 2 章 数据分析与数据挖掘工具··························································14
2.1 工业大数据的特点··········································································15
2.2 工业大数据挖掘的定义及过程···························································17
2.3 工业数据的特征分析·······································································18
2.3.1 工业数据的统计描述 ···································································18
2.3.2 工业数据的相关性分析 ································································20
2.4 工业数据的预处理··········································································23
2.4.1 异常值处理 ···············································································23
工业数据异常值的处理案例 ·····························································25
2.4.2 缺失值处理 ···············································································26
工业数据缺失值的处理案例 ·····························································27
2.4.3 数据归一化处理 ·········································································28
2.4.4 不等时距数据处理 ······································································28
工业数据不等时距处理案例·····························································.29
2.4.5 离群点检测···············································································.32
2.4.6 不平衡数据集检测······································································.34
2.4.7 数据降维处理············································································.36
2.5 假设检验····················································································.41
2.5.1 假设检验的基本原理···································································.41
2.5.2 假设检验的一般步骤···································································.42
2.5.3 假设检验的种类·········································································.42
2.6 多变量分析模型 ··········································································.44
2.6.1 线性模型··················································································.44
2.6.2 广义线性模型············································································.45
2.6.3 线性混合效应模型······································································.47
2.7 最大似然估计··············································································.48
2.8 关联分析····················································································.49
2.8.1 关联规则挖掘···········································································.·51
2.8.2 关联规则算法···········································································.·52
2.8.3 时序关联规则算法······································································.54
2.8.4 一维时序关联规则······································································.56
2.8.5 多维时序关联规则······················································.··············.59
2.9 数据分析系统的体系架构 ··············································.··············.64
第 3 章 机器学习 ····························································.···············.65
3.1 人类的思考过程与机器学习的过程 ···················································.65
3.2 机器学习的知识体系 ···················································.················.67
3.3 Python 语言的优势·········································································.68
3.4 工业人工智能的有监督学习算法 ·······················································.68
3.4.1 决策树算法···············································································.··70
决策树算法的应用案例：判断影响打网球的相关因素····························73
3.4.2 回归算法·····················································································75
3.4.3 支持向量机算法 ··········································································80
有监督学习算法的工业应用案例······························································86
3.5 工业人工智能的无监督学习算法·························································87
3.5.1 聚类算法 ···················································································87
3.5.2 自动编码器 ················································································94
无监督学习算法的工业应用案例·······························································95
3.6 机器学习的主要挑战及应对方法··························································97
3.6.1 机器学习的主要挑战 ·····································································97
3.6.2 应对挑战的主要方法 ····································································100
第 4 章 深度学习········································································.·······103
4.1 深度学习的核心·····································································.········103
4.2 深度学习的常用网络：卷积神经网络····················································106
4.2.1 卷积神经网络的结构 ·····································································107
4.2.2 卷积神经网络的关键技术 ·······························································109
4.2.3 卷积神经网络的训练 ·····································································112
卷积神经网络的工业应用案例························.·································113
4.3 深度学习的常用网络：循环神经网络··················.································115
4.3.1 循环神经网络的结构 ····································. ·······························115
4.3.2 循环神经网络的优化 ·····································································117
循环神经网络的工业应用案例··························································120
4.4 深度学习的常用网络：受限玻尔兹曼机·················································126
4.4.1 受限玻尔兹曼机的分类 ··································································126
4.4.2 受限玻尔兹曼机的训练 ··································································131
4.5 深度学习的常用网络：深度置信网络····················································134
4.5.1 深度置信网络的构建 ·····································································134
4.5.2 深度置信网络的训练 ·····································································135
深度置信网络的工业应用案例··························································137
4.6 深度学习的常用框架·········································································143
4.6.1 Theano·····················································································.143
4.6.2 TensorFlow··············································································. 144
4.6.3 Keras ·······················································································.146
4.6.4 Caffe/Caffe2···········································································. ·146
4.6.5 MXNet ····················································································. 147
4.6.6 CNTK······················································································. 148
第 5 章 工业人工智能面临的挑战 ···························································149
5.1 工业人工智能带来的变革 ·································································.149
5.2 工业人工智能面临的挑战 ·································································.150
参考文献·······························································································153