書馨卡幫你省薪 2024個(gè)人購(gòu)書報(bào)告 2024中圖網(wǎng)年度報(bào)告
歡迎光臨中圖網(wǎng) 請(qǐng) | 注冊(cè)
> >
新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn)

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn)

出版社：清華大學(xué)出版社出版時(shí)間：2020-11-01
開本： 其他 頁(yè)數(shù)： 256
中 圖 價(jià):¥43.6(4.9折) 定價(jià)  ¥89.0 登錄后可看到會(huì)員價(jià)
加入購(gòu)物車 收藏
運(yùn)費(fèi)6元，滿39元免運(yùn)費(fèi)
?新疆、西藏除外
溫馨提示：5折以下圖書主要為出版社尾貨，大部分為全新（有塑封/無(wú)塑封），個(gè)別圖書品相8-9成新、切口
有劃線標(biāo)記、光盤等附件不全詳細(xì)品相說(shuō)明>>
本類五星書更多>

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn) 版權(quán)信息

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn) 本書特色

中國(guó)人工智能學(xué)會(huì)機(jī)器學(xué)習(xí)專業(yè)委員會(huì)主任 陳松燦 中國(guó)計(jì)算機(jī)學(xué)會(huì)大數(shù)據(jù)專家委員會(huì)副主任 陳恩紅 好未來(lái)集團(tuán)副總裁兼開放平臺(tái)事業(yè)部總裁 黃琰 澳大利亞科學(xué)院院士， 悉尼大學(xué)教授 陶大程 劍橋大學(xué)教授、谷歌AI 大腦團(tuán)隊(duì)負(fù)責(zé)人 卓賓??加拉馬尼 聯(lián)袂推薦

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn) 內(nèi)容簡(jiǎn)介

本書全面介紹自動(dòng)機(jī)器學(xué)習(xí)，主要包含自動(dòng)機(jī)器學(xué)習(xí)的方法、實(shí)際可用的自動(dòng)機(jī)器學(xué)習(xí)系統(tǒng)及目前所面臨的挑戰(zhàn)。在自動(dòng)機(jī)器學(xué)習(xí)方法中，本書涵蓋超參優(yōu)化、元學(xué)習(xí)、神經(jīng)網(wǎng)絡(luò)架構(gòu)搜索三個(gè)部分，每一部分都包括詳細(xì)的內(nèi)容介紹、原理解讀、具體運(yùn)用方法和存在的問(wèn)題等。此外，本書還具體介紹了現(xiàn)有的各種可用的AutoML系統(tǒng)，如Auto-sklearn、Auto-WEKA及Auto-Net等，并且本書很后一章詳細(xì)介紹了具有代表性的AutoML挑戰(zhàn)賽及挑戰(zhàn)賽結(jié)果背后所蘊(yùn)含的理念，有助于從業(yè)者設(shè)計(jì)出自己的AutoML系統(tǒng)。 本書英文版是靠前上本介紹自動(dòng)機(jī)器學(xué)習(xí)的英文書，內(nèi)容全面且翔實(shí)，尤為重要的是涵蓋了近期新的AutoML領(lǐng)域進(jìn)展和難點(diǎn)。本書作者和譯者學(xué)術(shù)背景扎實(shí)，保證了本書的內(nèi)容質(zhì)量。 對(duì)于初步研究者，本書可以作為其研究自動(dòng)機(jī)器學(xué)習(xí)方法的背景知識(shí)和起點(diǎn)；對(duì)于工業(yè)界從業(yè)人員，本書全面介紹了AutoML系統(tǒng)及其實(shí)際應(yīng)用要點(diǎn)；對(duì)于已經(jīng)從事自動(dòng)機(jī)器學(xué)習(xí)的研究者，本書可以提供一個(gè)AutoML近期新研究成果和進(jìn)展的概覽？傮w來(lái)說(shuō)，本書受眾較為廣泛，既可以作為入門書，也可以作為專業(yè)人士的參考書。

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn) 目錄

目 錄


自動(dòng)機(jī)器學(xué)習(xí)方法


第1章 超參優(yōu)化 ··································2


1.1 引言 ··············································2


1.2 問(wèn)題定義 ·······································4


1.2.1 優(yōu)化替代方案：集成與邊緣化 ·············5


1.2.2 多目標(biāo)優(yōu)化 ···········································5


1.3 黑盒超參優(yōu)化 ·······························6


1.3.1 免模型的黑盒優(yōu)化方法 ························6


1.3.2 貝葉斯優(yōu)化 ···········································8


1.4 多保真度優(yōu)化 ······························13


1.4.1 基于學(xué)習(xí)曲線預(yù)測(cè)的早停法 ··············14


1.4.2 基于Bandit的選擇方法 ·····················15


1.4.3 保真度的適應(yīng)性選擇 ··························17


1.5 AutoML的相關(guān)應(yīng)用 ····················18


1.6 探討與展望 ··································20


1.6.1 基準(zhǔn)測(cè)試和基線模型 ··························21


1.6.2 基于梯度的優(yōu)化 ··································22


1.6.3 可擴(kuò)展性 ·············································22


1.6.4 過(guò)擬合和泛化性 ··································23


1.6.5 任意尺度的管道構(gòu)建 ··························24


參考文獻(xiàn)···············································25


第2章 元學(xué)習(xí) ···································36


2.1 引言 ·············································36


2.2 模型評(píng)估中學(xué)習(xí) ··························37


2.2.1 獨(dú)立于任務(wù)的推薦 ······························38


2.2.2 配置空間的設(shè)計(jì) ··································39


2.2.3 配置遷移 ·············································39


2.2.4 學(xué)習(xí)曲線 ·············································42


2.3 任務(wù)特性中學(xué)習(xí) ··························43


2.3.1 元特征 ·················································43


2.3.2 元特征的學(xué)習(xí) ·····································44


2.3.3 基于相似任務(wù)熱啟動(dòng)優(yōu)化過(guò)程 ···········46


2.3.4 元模型 ·················································48


2.3.5 管道合成 ·············································49


2.3.6 調(diào)優(yōu)與否 ·············································50


2.4 先前模型中學(xué)習(xí) ··························50


**篇



XVI


2.4.1 遷移學(xué)習(xí) ·············································51


2.4.2 針對(duì)神經(jīng)網(wǎng)絡(luò)的元學(xué)習(xí) ······················51


2.4.3 小樣本學(xué)習(xí) ·········································52


2.4.4 不止于監(jiān)督學(xué)習(xí) ··································54


2.5 總結(jié) ·············································55


參考文獻(xiàn)···············································56


第3章 神經(jīng)網(wǎng)絡(luò)架構(gòu)搜索 ··················68


3.1 引言 ·············································68


3.2 搜索空間 ······································69


3.3 搜索策略 ······································73


3.4 性能評(píng)估策略 ······························76


3.5 未來(lái)方向 ······································78


參考文獻(xiàn)···············································80


自動(dòng)機(jī)器學(xué)習(xí)系統(tǒng)


第4章 Auto-WEKA ···························86


4.1 引言 ·············································86


4.2 準(zhǔn)備工作 ······································88


4.2.1 模型選擇 ·············································88


4.2.2 超參優(yōu)化 ·············································88


4.3 算法選擇與超參優(yōu)化結(jié)合

（CASH） ···································89


4.4 Auto-WEKA ·································91


4.5 實(shí)驗(yàn)評(píng)估 ······································93


4.5.1 對(duì)比方法 ·············································94


4.5.2 交叉驗(yàn)證性能 ·····································96


4.5.3 測(cè)試性能 ·············································96


4.6 總結(jié) ·············································98


參考文獻(xiàn)···············································98


第5章 Hyperopt-sklearn ·················101


5.1 引言 ···········································101


5.2 Hyperopt背景 ····························102


5.3 Scikit-Learn模型選擇 ···············103


5.4 使用示例 ····································105


5.5 實(shí)驗(yàn) ···········································109


5.6 討論與展望 ································111


5.7 總結(jié) ···········································114


參考文獻(xiàn)·············································114


第6章 Auto-sklearn ························116


6.1 引言 ···········································116


6.2 CASH問(wèn)題 ································118


6.3 改進(jìn) ···········································119


6.3.1 元學(xué)習(xí)步驟 ········································119


6.3.2 集成的自動(dòng)構(gòu)建 ································121


6.4 Auto-sklearn系統(tǒng) ······················121


6.5 Auto-sklearn的對(duì)比試驗(yàn) ···········125


6.6 Auto-sklearn改進(jìn)項(xiàng)的評(píng)估 ·······127


6.7 Auto-sklearn組件的詳細(xì)分析 ···129


6.8 討論與總結(jié) ································134


6.8.1 討論 ···················································134


第二篇



XVII


6.8.2 使用示例 ···········································134


6.8.3 Auto-sklearn的擴(kuò)展 ··························135


6.8.4 總結(jié)與展望 ·······································136


參考文獻(xiàn)·············································136


第7章 Auto-Net ······························140


7.1 引言 ···········································140


7.2 Auto-Net 1.0 ·······························142


7.3 Auto-Net 2.0 ·······························144


7.4 實(shí)驗(yàn) ···········································151


7.4.1 基線評(píng)估 ···········································151


7.4.2 AutoML競(jìng)賽上的表現(xiàn) ·····················152


7.4.3 Auto-Net 1.0與Auto-Net 2.0的對(duì)比····154


7.5 總結(jié) ···········································155


參考文獻(xiàn)·············································156


第8章 TPOT ··································160


8.1 引言 ···········································160


8.2 方法 ···········································161


8.2.1 機(jī)器學(xué)習(xí)管道算子 ····························161


8.2.2 構(gòu)建基于樹的管道 ····························162


8.2.3 優(yōu)化基于樹的管道 ····························163


8.2.4 基準(zhǔn)測(cè)試數(shù)據(jù) ···································163


8.3 實(shí)驗(yàn)結(jié)果 ····································164


8.4 總結(jié)與展望 ································167


參考文獻(xiàn)·············································168


第9章 自動(dòng)統(tǒng)計(jì) ······························170


9.1 引言 ···········································170


9.2 自動(dòng)統(tǒng)計(jì)項(xiàng)目的基本結(jié)構(gòu) ·········172


9.3 應(yīng)用于時(shí)序數(shù)據(jù)的自動(dòng)統(tǒng)計(jì) ·····173


9.3.1 核函數(shù)上的語(yǔ)法 ································173


9.3.2 搜索和評(píng)估過(guò)程 ································175


9.3.3 生成自然語(yǔ)言性的描述 ····················175


9.3.4 與人類比較 ·······································177


9.4 其他自動(dòng)統(tǒng)計(jì)系統(tǒng) ····················178


9.4.1 核心組件 ···········································178


9.4.2 設(shè)計(jì)挑戰(zhàn) ···········································179


9.5 總結(jié) ···········································180


參考文獻(xiàn)·············································180


自動(dòng)機(jī)器學(xué)習(xí)挑戰(zhàn)賽


第10章 自動(dòng)機(jī)器學(xué)習(xí)挑戰(zhàn)賽分析 ···186


10.1 引言··········································187


10.2 問(wèn)題形式化和概述 ···················190


10.2.1 問(wèn)題的范圍 ·····································190


10.2.2 全模型選擇 ·····································191


10.2.3 超參優(yōu)化 ·········································192


10.2.4 模型搜索策略 ·································193


10.3 數(shù)據(jù)··········································197


10.4 挑戰(zhàn)賽協(xié)議 ······························201


10.4.1 時(shí)間預(yù)算和計(jì)算資源 ······················201


10.4.2 評(píng)分標(biāo)準(zhǔn) ·········································202


10.4.3 挑戰(zhàn)賽2015/2016中的輪次和階段 ····205


第三篇



10.4.4 挑戰(zhàn)賽2018中的階段 ····················206


10.5 結(jié)果··········································207


10.5.1 挑戰(zhàn)賽2015/2016上的得分 ···········207


10.5.2 挑戰(zhàn)賽2018上的得分 ····················209


10.5.3 數(shù)據(jù)集/任務(wù)的難度 ·······················210


10.5.4 超參優(yōu)化 ·········································217


10.5.5 元學(xué)習(xí) ·············································217


10.5.6 挑戰(zhàn)賽中使用的方法 ······················219


10.6 討論··········································224


10.7 總結(jié)··········································226


參考文獻(xiàn)·············································229





展開全部

新時(shí)代·技術(shù)新未來(lái)自動(dòng)機(jī)器學(xué)習(xí)(AutoML):方法、系統(tǒng)與挑戰(zhàn) 作者簡(jiǎn)介

弗蘭克??亨特，德國(guó)弗萊堡大學(xué)教授，機(jī)器學(xué)習(xí)實(shí)驗(yàn)室負(fù)責(zé)人。主要研究統(tǒng)計(jì)機(jī)器學(xué)習(xí)、知識(shí)表示、自動(dòng)機(jī)器學(xué)習(xí)及其應(yīng)用，獲得第一屆（2015/2016）、第二屆（2018/2019）自動(dòng)機(jī)器學(xué)習(xí)比賽的世界冠軍。 拉斯??特霍夫，美國(guó)懷俄明大學(xué)助理教授。主要研究深度學(xué)習(xí)、自動(dòng)機(jī)器學(xué)習(xí)，致力于構(gòu)建領(lǐng)先且健壯的機(jī)器學(xué)習(xí)系統(tǒng)，領(lǐng)導(dǎo)Auto-WEKA項(xiàng)目的開發(fā)和維護(hù)。 華昆??萬(wàn)赫仁，荷蘭埃因霍溫理工大學(xué)助理教授。主要研究機(jī)器學(xué)習(xí)的逐步自動(dòng)化，創(chuàng)建了共享數(shù)據(jù)開源平臺(tái)OpenML.org，并獲得微軟Azure研究獎(jiǎng)和亞馬遜研究獎(jiǎng)。 譯者簡(jiǎn)介 何明，中國(guó)科學(xué)技術(shù)大學(xué)博士，目前為上海交通大學(xué)電子科學(xué)與技術(shù)方向博士后研究人員、好未來(lái)教育集團(tuán)數(shù)據(jù)中臺(tái)人工智能算法研究員。 劉淇，中國(guó)科學(xué)技術(shù)大學(xué)計(jì)算機(jī)學(xué)院特任教授，博士生導(dǎo)師，中國(guó)計(jì)算機(jī)學(xué)會(huì)大數(shù)據(jù)專家委員會(huì)委員，中國(guó)人工智能學(xué)會(huì)機(jī)器學(xué)習(xí)專業(yè)委員會(huì)委員。

商品評(píng)論(0條)
暫無(wú)評(píng)論……
書友推薦
編輯推薦
返回頂部
中圖網(wǎng)
在線客服