《工業人工智慧概論》是2020年1月電子工業出版社出版的圖書，作者是韓英華。
基本介紹
- 中文名：工業人工智慧概論
- 作者：韓英華
- 出版社：電子工業出版社
- 出版時間：2020年1月
- 頁數：164 頁
- 定價：56 元
- 開本：16 開
- ISBN：9787121381621
內容簡介,圖書目錄,
內容簡介
本書以人工智慧技術在工業中的套用為出發點，系統、深入地闡述了工業人工智慧的關鍵技術，並給出了大量的套用案例。全書共 5 章，包括緒論、數據分析與數據挖掘工具、機器學習、深度學習和工業人工智慧面臨的挑戰。
本書可作為相關專業的本科生及研究生學習工業人工智慧的入門教材，也可作為專業技術人員了解工業人工智慧的培訓教材和參考書，還可作為對工業人工智慧感興趣的各界人士的普及性讀物。
圖書目錄
第 1 章 緒論·····················································································1
1.1 人工智慧的內涵及發展····································································1
1.2 工業人工智慧的內涵及發展······························································4
1.2.1 工業人工智慧的發展背景 ·····························································4
1.2.2 工業人工智慧的發展歷程 ·····························································6
1.2.3 工業人工智慧與傳統人工智慧的區別················································7
1.3 工業人工智慧的算法功能和典型套用··················································8
1.4 工業人工智慧的知識體系································································11
1.5 工業人工智慧的關鍵技術································································12
第 2 章 數據分析與數據挖掘工具··························································14
2.1 工業大數據的特點··········································································15
2.2 工業大數據挖掘的定義及過程···························································17
2.3 工業數據的特徵分析·······································································18
2.3.1 工業數據的統計描述 ···································································18
2.3.2 工業數據的相關性分析 ································································20
2.4 工業數據的預處理··········································································23
2.4.1 異常值處理 ···············································································23
工業數據異常值的處理案例 ·····························································25
2.4.2 缺失值處理 ···············································································26
工業數據缺失值的處理案例 ·····························································27
2.4.3 數據歸一化處理 ·········································································28
2.4.4 不等時距數據處理 ······································································28
工業數據不等時距處理案例·····························································.29
2.4.5 離群點檢測···············································································.32
2.4.6 不平衡數據集檢測······································································.34
2.4.7 數據降維處理············································································.36
2.5 假設檢驗····················································································.41
2.5.1 假設檢驗的基本原理···································································.41
2.5.2 假設檢驗的一般步驟···································································.42
2.5.3 假設檢驗的種類·········································································.42
2.6 多變數分析模型 ··········································································.44
2.6.1 線性模型··················································································.44
2.6.2 廣義線性模型············································································.45
2.6.3 線性混合效應模型······································································.47
2.7 最大似然估計··············································································.48
2.8 關聯分析····················································································.49
2.8.1 關聯規則挖掘···········································································.·51
2.8.2 關聯規則算法···········································································.·52
2.8.3 時序關聯規則算法······································································.54
2.8.4 一維時序關聯規則······································································.56
2.8.5 多維時序關聯規則······················································.··············.59
2.9 數據分析系統的體系架構 ··············································.··············.64
第 3 章 機器學習 ····························································.···············.65
3.1 人類的思考過程與機器學習的過程 ···················································.65
3.2 機器學習的知識體系 ···················································.················.67
3.3 Python 語言的優勢·········································································.68
3.4 工業人工智慧的有監督學習算法 ·······················································.68
3.4.1 決策樹算法···············································································.··70
決策樹算法的套用案例：判斷影響打網球的相關因素····························73
3.4.2 回歸算法·····················································································75
3.4.3 支持向量機算法 ··········································································80
有監督學習算法的工業套用案例······························································86
3.5 工業人工智慧的無監督學習算法·························································87
3.5.1 聚類算法 ···················································································87
3.5.2 自動編碼器 ················································································94
無監督學習算法的工業套用案例·······························································95
3.6 機器學習的主要挑戰及應對方法··························································97
3.6.1 機器學習的主要挑戰 ·····································································97
3.6.2 應對挑戰的主要方法 ····································································100
第 4 章 深度學習········································································.·······103
4.1 深度學習的核心·····································································.········103
4.2 深度學習的常用網路：卷積神經網路····················································106
4.2.1 卷積神經網路的結構 ·····································································107
4.2.2 卷積神經網路的關鍵技術 ·······························································109
4.2.3 卷積神經網路的訓練 ·····································································112
卷積神經網路的工業套用案例························.·································113
4.3 深度學習的常用網路：循環神經網路··················.································115
4.3.1 循環神經網路的結構 ····································. ·······························115
4.3.2 循環神經網路的最佳化 ·····································································117
循環神經網路的工業套用案例··························································120
4.4 深度學習的常用網路：受限玻爾茲曼機·················································126
4.4.1 受限玻爾茲曼機的分類 ··································································126
4.4.2 受限玻爾茲曼機的訓練 ··································································131
4.5 深度學習的常用網路：深度置信網路····················································134
4.5.1 深度置信網路的構建 ·····································································134
4.5.2 深度置信網路的訓練 ·····································································135
深度置信網路的工業套用案例··························································137
4.6 深度學習的常用框架·········································································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 工業人工智慧面臨的挑戰 ···························································149
5.1 工業人工智慧帶來的變革 ·································································.149
5.2 工業人工智慧面臨的挑戰 ·································································.150
參考文獻·······························································································153
