《邊雲智慧型數據分析與套用》是電子工業出版社出版的圖書，作者是沈鈞戈 等。
基本介紹
- 中文名：邊雲智慧型數據分析與套用
- 作者：沈鈞戈 等
- 出版時間：2023年8月
- 出版社：電子工業出版社
- 頁數：216 頁
- 字數：216千字
- ISBN：9787121460425
- 開本：16 開
內容簡介,圖書目錄,
內容簡介
隨著“十四五”規劃綱要中提出“協同發展雲服務與邊緣計算服務”的觀點，邊雲智慧型已成為未來發展的重要趨勢。本書依託於政策大背景，旨在向讀者介紹邊雲智慧型的基礎知識和套用。書中分為四個篇章，第一篇章介紹了邊雲架構的骨架和基礎概念，第二篇章介紹了人工智慧算法和深度學習模型，第三篇章介紹了雲端決策算法和邊緣端輕量化算法，第四篇章介紹了邊雲智慧型在智慧教育領域的套用。本書可以使讀者了解邊雲計算的基本概念和原理邏輯，熟悉基本的人工智慧計算方法和數據分析的邏輯和運用場景。通過數據科學的思路和方法，讀者可以將無人系統的數據智慧型化套用提升，並培養數據導向思維方式，為未來學習智慧型無人系統科學與技術學科打下基礎。 本書目標明確，技術先進，強調課程思政和潤物無聲的教育理念，旨在提高學生的數據科學素養和“用數據”的能力。本書面向智慧型無人系統科學與技術專業的研究生，涵蓋人工智慧、大數據分析、數據挖掘和邊雲計算等學科，具有交叉性的特點。同時，資深從業者也可將其作為參考書籍。
圖書目錄
第 1 章 緒論 ····························································································1
1.1 邊雲智慧型產生的大背景····································································1
1.1.1 新一代信息技術的快速發展·····················································2
1.1.2 國家政策的支持與引導···························································6
1.2 邊雲智慧型······················································································7
1.3 邊雲智慧型的發展·············································································9
1.3.1 邊雲智慧型的三大發展階段························································9
1.3.2 城市大腦··········································································.11
1.4 “智慧型+”新潮頭··········································································.13
1.4.1 “智慧型+”技術新融合···························································.13
1.4.2 多維度場景套用·································································.14
本章習題··························································································.15
第 2 章 邊雲架構 ···················································································.16
2.1 系統工程方法論··········································································.17
2.1.1 概述 ················································································.17
2.1.2 基本方法··········································································.17
2.2 邊雲智慧型體系架構模型·································································.20
2.2.1 概念框架··········································································.20
2.2.2 層次結構··········································································.22
2.3 協同模式···················································································.23
2.3.1 “雲-邊”協同 ····································································.24
2.3.2 “邊-邊”協同 ····································································.25
2.3.3 “邊-端”協同 ····································································.27
2.3.4 “雲-邊-端”協同 ································································.28
2.3.5 度量指標··········································································.28
2.4 邊雲智慧型架構套用·······································································.30
2.4.1 “雲-邊-端”區塊鏈 ·····························································.30
2.4.2 “雲-邊-端”一體化機器人系統 ··············································.32
本章習題··························································································.33
第 3 章 深度學習 ···················································································.35
3.1 深度學習概念·············································································.36
3.1.1 人工智慧與機器學習···························································.36
3.1.2 深度學習··········································································.37
3.1.3 神經網路··········································································.39
3.2 前饋神經網路·············································································.39
3.2.1 感知機模型·······································································.39
3.2.2 反向傳播··········································································.42
3.2.3 卷積神經網路····································································.44
3.2.4 幾種典型的卷積神經網路·····················································.47
3.3 反饋神經網路·············································································.50
3.3.1 循環神經網路····································································.50
3.3.2 長短期神經網路·································································.53
3.4 Transformer 神經網路 ···································································.56
3.4.1 編碼器單元與解碼器單元·····················································.58
3.4.2 多頭注意力機制·································································.59
3.4.3 非參位置編碼····································································.60
本章習題··························································································.61
第 4 章 自然語言處理 ·············································································.62
4.1 自然語言處理概述·······································································.63
4.1.1 自然語言處理簡介······························································.63
4.1.2 自然語言處理的發展歷史·····················································.74
4.1.3 自然語言處理的套用及面臨的挑戰·········································.76
4.2 文本挖掘···················································································.79
4.2.1 文本挖掘簡介····································································.79
4.2.2 文本挖掘算法····································································.81
4.3 機器翻譯···················································································.87
4.3.1 機器翻譯簡介····································································.87
4.3.2 機器翻譯算法····································································.89
4.4 自動問答系統·············································································.93
4.4.1 自動問答系統簡介······························································.93
4.4.2 自動問答系統模型······························································.95
4.5 語音識別···················································································101
4.5.1 語音識別簡介····································································102
4.5.2 語音識別算法····································································103
本章習題··························································································105
第 5 章 計算機視覺 ················································································107
5.1 計算機視覺概述··········································································107
5.1.1 計算機視覺簡介·································································108
5.1.2 計算機視覺的發展歷史························································109
5.1.3 計算機視覺的套用及面臨的挑戰···········································.110
5.2 圖像分類··················································································.114
5.2.1 圖像分類簡介···································································.114
5.2.2 圖像分類算法···································································.115
5.3 目標檢測··················································································.119
5.3.1 目標檢測簡介···································································.119
5.3.2 目標檢測算法····································································120
5.4 圖像分割···················································································123
5.4.1 圖像分割簡介····································································123
5.4.2 圖像分割算法····································································124
5.5 目標跟蹤···················································································125
5.5.1 目標跟蹤簡介····································································126
5.5.2 目標跟蹤算法····································································126
本章習題··························································································128
第 6 章 邊緣輕量化 ················································································129
6.1 邊緣輕量化的簡介·······································································129
6.1.1 邊緣端對輕量化的需求························································129
6.1.2 什麼是邊緣輕量化······························································130
6.2 模型壓縮方法·············································································131
6.2.1 量化和二值化····································································131
6.2.2 網路剪枝··········································································131
6.2.3 低秩因子分解····································································132
6.2.4 參數共享··········································································133
6.2.5 蒸餾學習··········································································133
6.2.6 加速網路設計····································································134
6.3 模型壓縮舉例·············································································137
6.3.1 知識蒸餾··········································································137
6.3.2 深度壓縮··········································································139
6.3.3 MNASNet ·········································································143
本章習題··························································································145
第 7 章 雲端決策 ···················································································146
7.1 雲端決策簡介·············································································147
7.1.1 雲端決策的重要性······························································147
7.1.2 雲端決策的特點·································································147
7.2 雲端決策——大數據挖掘······························································149
7.2.1 回歸分析··········································································149
7.2.2 聚類 ················································································150
7.2.3 關聯規則··········································································152
7.3 雲端決策——推薦算法·································································154
7.3.1 基於統計的推薦算法···························································155
7.3.2 基於協同過濾的推薦系統·····················································155
7.3.3 基於內容的推薦系統···························································156
7.3.4 基於關聯規則的推薦系統·····················································158
7.3.5 基於網路結構的推薦系統·····················································158
本章習題··························································································159
第 8 章 邊雲智慧型賦能智慧教室 ·································································160
8.1 智慧教室的形成背景與邊雲框架·····················································161
8.1.1 智慧教室政策支持與特徵分析 ··············································162
8.1.2 基於邊雲智慧型的智慧教室框架 ··············································164
8.1.3 基於邊雲智慧型建設的智慧教室目標願景 ··································166
8.2 智慧教室的邊緣端感知技術與套用··················································166
8.2.1 無感考勤、表情感知與異常行為識別 ·····································167
8.2.2 邊緣端感知模型的壓縮與輕量化 ···········································172
8.3 智慧教室的雲端決策技術與套用·····················································174
8.3.1 “教育大腦”大數據分析決策方法··········································174
8.3.2 個性化推薦、學習評價與師生互動套用 ··································176
8.4 “邊雲智慧型+”前景展望·································································178
8.4.1 邊雲智慧型賦能智慧交通························································178
8.4.2 邊雲智慧型賦能智慧安防························································185
本章習題··························································································190
習題答案································································································191
