定 價：79 元
叢書名：經(jīng)典譯叢·人工智能與智能系統(tǒng)
- 作者：（美）Adnan Masood（阿德南·馬蘇德）
- 出版時間：2023/6/1
- ISBN：9787121457050
- 出 版 社：電子工業(yè)出版社
- 中圖法分類：TP181
- 頁碼：188
- 紙張：
- 版次：01
- 開本：16開
本書重點講解基于云平臺的超參數(shù)優(yōu)化、神經(jīng)構(gòu)架搜索以及算法選擇等內(nèi)容，是自動機器學習的基本任務(wù)。介紹了基于三個主要云服務(wù)提供商（包括 Microsoft Azure、Amazon Web Services (AWS) 和 Google Cloud Platform）進行 AutoML，同時部署 ML 模型和管道，具有較強的實用性。在應(yīng)用場景中評估 AutoML 方面，例如算法選擇、自動特征化和超參數(shù)調(diào)整，并區(qū)分云和 OSS 產(chǎn)品等。本書適用于從事機器學習或人工智能方向的數(shù)據(jù)科學家或工程師學習，也適合學生或行業(yè)初學者進行入門學習實踐。
Adnan Masood，工程師、教師、研究員，在金融技術(shù)和開發(fā)大型系統(tǒng)方面擁有超過20年的全球經(jīng)驗。被微軟評為微軟區(qū)域總監(jiān)和微軟人工智能領(lǐng)域最有價值專家。擔任UST-Global的首席人工智能官和首席架構(gòu)師，負責公司在認知計算、人工智能、機器學習和學術(shù)關(guān)系方面的整體戰(zhàn)略。與斯坦福人工智能實驗室、麻省理工學院CSAIL合作，領(lǐng)導數(shù)據(jù)科學家和工程師團隊構(gòu)建人工智能解決方案，以產(chǎn)生影響一系列業(yè)務(wù)、產(chǎn)品和計劃的商業(yè)價值和見解。在帕克大學教授數(shù)據(jù)科學，并在加州大學圣地亞哥分校教授Windows WCF課程。擔任《財富》500強企業(yè)和初創(chuàng)企業(yè)顧問。曾出版亞馬遜編程語言暢銷書《f#函數(shù)編程》。
Adnan Masood，工程師、教師、研究員，在金融技術(shù)和開發(fā)大型系統(tǒng)方面擁有超過20年的全球經(jīng)驗。被微軟評為微軟區(qū)域總監(jiān)和微軟人工智能領(lǐng)域最有價值專家。擔任UST-Global的首席人工智能官和首席架構(gòu)師，負責公司在認知計算、人工智能、機器學習和學術(shù)關(guān)系方面的整體戰(zhàn)略。與斯坦福人工智能實驗室、麻省理工學院CSAIL合作，領(lǐng)導數(shù)據(jù)科學家和工程師團隊構(gòu)建人工智能解決方案，以產(chǎn)生影響一系列業(yè)務(wù)、產(chǎn)品和計劃的商業(yè)價值和見解。在帕克大學教授數(shù)據(jù)科學，并在加州大學圣地亞哥分校教授Windows WCF課程。擔任《財富》500強企業(yè)和初創(chuàng)企業(yè)顧問。曾出版亞馬遜編程語言暢銷書《f#函數(shù)編程》。
第 1 章 走進自動機器學習··············································································.1
1.1 機器學習開發(fā)生命周期 ·······································································.1
1.2 自動機器學習簡介 ·············································································.2
1.3 自動機器學習的工作原理 ····································································.3
1.4 數(shù)據(jù)科學的大眾化 ·············································································.5
1.5 揭穿自動機器學習的迷思 ····································································.5
1.6 自動機器學習生態(tài)系統(tǒng) ·······································································.6
1.7 小結(jié) ·······························································································11
第 2 章 自動機器學習、算法和技術(shù)··································································12
2.1 自動機器學習概述 ·············································································12
2.2 自動特征工程 ···················································································15
2.3 超參數(shù)優(yōu)化 ······················································································16
2.4 神經(jīng)架構(gòu)搜索 ···················································································18
2.5 小結(jié) ·······························································································19
第 3 章 使用開源工具和庫進行自動機器學習······················································20
3.1 技術(shù)要求 ·························································································20
3.2 自動機器學習的開源生態(tài)系統(tǒng) ······························································21
3.3 TPOT······························································································22
3.4 Featuretools ······················································································29
3.5 Microsoft NNI ···················································································32
3.6 auto-sklearn ······················································································38
3.7 AutoKeras ························································································41
3.8 Ludwig ····························································································44
3.9 AutoGluon························································································44
3.10 小結(jié)······························································································44
第 4 章 Azure Machine Learning········································································45
4.1 Azure Machine Learning 入門 ································································45
4.2 Azure Machine Learning 棧 ···································································46
4.3 Azure Machine Learning 服務(wù) ································································50
4.4 使用 Azure Machine Learning 建模 ·························································56
4.5 使用 Azure Machine Learning 部署和測試模型 ··········································68
4.6 小結(jié) ·······························································································70
第 5 章 使用 Azure 進行自動機器學習 ·······························································71
5.1 Azure 中的自動機器學習 ·····································································71
5.2 使用自動機器學習進行時間序列預測 ·····················································85
5.3 小結(jié) ·······························································································97
第 6 章 使用 AWS 進行機器學習 ······································································98
6.1 AWS 環(huán)境中的機器學習······································································98
6.2 開始使用 AWS ···············································································.101
6.3 使用 Amazon SageMaker Autopilot·······················································.109
6.4 使用 Amazon SageMaker JumpStart······················································.111
6.5 小結(jié) ····························································································.111
第 7 章 使用 Amazon SageMaker Autopilot 進行自動機器學習······························.113
7.1 技術(shù)要求 ······················································································.113
7.2 創(chuàng)建 Amazon SageMaker Autopilot 受限實驗··········································.113
7.3 創(chuàng)建 AutoML 實驗 ··········································································.120
7.4 運行 SageMaker Autopilot 實驗并部署模型············································.123
7.5 構(gòu)建并運行 SageMaker Autopilot 實驗··················································.126
7.6 小結(jié) ····························································································.132
第 8 章 使用 Google Cloud Platform 進行機器學習 ·············································.134
8.1 Google Cloud Platform 使用入門 ·························································.134
8.2 使用 GCP 實現(xiàn) AI 和 ML··································································.137
8.3 Google Cloud AI Platform 和 AI Hub·····················································.139
8.4 Google Cloud AI Platform 使用入門 ·····················································.141
8.5 使用 Google Cloud 進行 AutoML ························································.144
8.6 小結(jié) ····························································································.146
第 9 章 使用 GCP 進行自動機器學習······························································.147
9.1 Google Cloud AutoML Tables······························································.147
9.2 創(chuàng)建 AutoML Tables 實驗··································································.148
9.3 了解 AutoML Tables 模型部署····························································.158
9.4 在 AutoML Tables 上使用 BigQuery 公共數(shù)據(jù)集 ·····································.162
9.5 自動機器學習做價格預測 ·································································.164
9.6 小結(jié) ····························································································.170
第 10 章 企業(yè)中的自動機器學習 ···································································.171
10.1 企業(yè)是否需要自動機器學習·····························································.171
10.2 自動機器學習——企業(yè)高級分析的加速器···········································.172
10.3 自動機器學習的挑戰(zhàn)和機遇·····························································.173
10.4 建立信任——自動機器學習中的模型可解釋性和透明度 ························.174
10.5 在企業(yè)中引入自動機器學習·····························································.176
10.6 總結(jié)與展望··················································································.177
書單推薦
