掃一掃
關注中圖網
官方微博
本類五星書更多>
-
>
全國計算機等級考試最新真考題庫模擬考場及詳解·二級MSOffice高級應用
-
>
決戰行測5000題(言語理解與表達)
-
>
軟件性能測試.分析與調優實踐之路
-
>
第一行代碼Android
-
>
JAVA持續交付
-
>
EXCEL最強教科書(完全版)(全彩印刷)
-
>
深度學習
蒙特卡羅方法與人工智能 版權信息
- ISBN：9787121470202
- 條形碼：9787121470202 ; 978-7-121-47020-2
- 裝幀：平裝-膠訂
- 冊數：暫無
- 重量：暫無
- 所屬分類：>
蒙特卡羅方法與人工智能 本書特色
《蒙特卡羅方法與人工智能》的原著作者朱松純教授在人工智能和計算機視覺領域享有盛譽，他的研究成果廣泛引用并影響了該領域的發展；從學術成果、榮譽和貢獻上來說，他是一位世界著名科學家。
本書由朱松純教授推薦西安交通大學人工智能學院教授、國家青年人才魏平翻譯，全面敘述了蒙特卡羅方法，包括序貫蒙特卡羅方法、馬爾可夫鏈蒙特卡羅方法基礎、Metropolis算法及其變體、吉布斯采樣器及其變體、聚類采樣方法、馬爾可夫鏈蒙特卡羅的收斂性分析、數據驅動的馬爾可夫鏈蒙特卡羅方法、哈密頓和朗之萬蒙特卡羅方法、隨機梯度學習和可視化能級圖等，文字精練、流暢，內容經典，有深度，是人工智能領域經典圖書，可適合計算機、人工智能、機器人等領域的教師、學生閱讀和參考，也適合相關領域的研究者和工業界的從業者閱讀。
蒙特卡羅方法與人工智能 內容簡介
本書全面敘述了蒙特卡羅方法，包括序貫蒙特卡羅方法、馬爾可夫鏈蒙特卡羅方法基礎、Metropolis算法及其變體、吉布斯采樣器及其變體、聚類采樣方法、馬爾可夫鏈蒙特卡羅的收斂性分析、數據驅動的馬爾可夫鏈蒙特卡羅方法、哈密頓和朗之萬蒙特卡羅方法、隨機梯度學習和可視化能級圖等。為了便于學習，每章都包含了不同領域的代表性應用實例。本書旨在統計學和計算機科學之間架起一座橋梁以彌合它們之間的鴻溝，以便將其應用于計算機視覺、計算機圖形學、機器學習、機器人學、人工智能等領域解決更廣泛的問題，同時使這些領域的科學家和工程師們更容易地利用蒙特卡羅方法加強他們的研究。 本書適合計算機、人工智能、機器人等領域的教師、學生閱讀和參考，也適合相關領域的研究者和工業界的從業者閱讀。
蒙特卡羅方法與人工智能 目錄
目 錄
第1 章 蒙特卡羅方法簡介··············································································.1
1.1 引言·······························································································.1
1.2 動機和目標······················································································.1
1.3 蒙特卡羅計算中的任務·······································································.2
1.3.1 任務1：采樣和模擬········································································.3
1.3.2 任務2：通過蒙特卡羅模擬估算未知量···················································.5
1.3.3 任務3：優化和貝葉斯推理································································.7
1.3.4 任務4：學習和模型估計···································································.8
1.3.5 任務5：可視化能級圖·····································································.9
本章參考文獻··························································································13
第2 章 序貫蒙特卡羅方法··············································································14
2.1 引言·······························································································14
2.2 一維密度采樣···················································································14
2.3 重要性采樣和加權樣本·······································································15
2.4 序貫重要性采樣（SIS） ······································································18
2.4.1 應用：表達聚合物生長的自避游走························································18
2.4.2 應用：目標跟蹤的非線性/粒子濾波·······················································20
2.4.3 SMC 方法框架總結·········································································23
2.5 應用：利用SMC 方法進行光線追蹤·······················································24
2.6 在重要性采樣中保持樣本多樣性···························································25
2.6.1 基本方法····················································································25
2.6.2 Parzen 窗討論··············································································28
2.7 蒙特卡羅樹搜索················································································29
2.7.1 純蒙特卡羅樹搜索··········································································30
2.7.2 AlphaGo ·····················································································32
2.8 本章練習·························································································33
本章參考文獻··························································································35
第3 章 馬爾可夫鏈蒙特卡羅方法基礎·······························································36
3.1 引言·······························································································36
蒙特卡羅方法與人工智能
·X ·
3.2 馬爾可夫鏈基礎················································································37
3.3 轉移矩陣的拓撲：連通與周期······························································38
3.4 Perron-Frobenius 定理··········································································41
3.5 收斂性度量······················································································42
3.6 連續或異構狀態空間中的馬爾可夫鏈·····················································44
3.7 各態遍歷性定理················································································45
3.8 通過模擬退火進行MCMC 優化·····························································46
3.9 本章練習·························································································49
本章參考文獻··························································································51
第4 章 Metropolis 算法及其變體······································································52
4.1 引言·······························································································52
4.2 Metropolis-Hastings 算法······································································52
4.2.1 原始Metropolis-Hastings 算法······························································53
4.2.2 Metropolis-Hastings 算法的另一形式·······················································54
4.2.3 其他接受概率設計··········································································55
4.2.4 Metropolis 算法設計中的關鍵問題·······························4
第1 章 蒙特卡羅方法簡介··············································································.1
1.1 引言·······························································································.1
1.2 動機和目標······················································································.1
1.3 蒙特卡羅計算中的任務·······································································.2
1.3.1 任務1：采樣和模擬········································································.3
1.3.2 任務2：通過蒙特卡羅模擬估算未知量···················································.5
1.3.3 任務3：優化和貝葉斯推理································································.7
1.3.4 任務4：學習和模型估計···································································.8
1.3.5 任務5：可視化能級圖·····································································.9
本章參考文獻··························································································13
第2 章 序貫蒙特卡羅方法··············································································14
2.1 引言·······························································································14
2.2 一維密度采樣···················································································14
2.3 重要性采樣和加權樣本·······································································15
2.4 序貫重要性采樣（SIS） ······································································18
2.4.1 應用：表達聚合物生長的自避游走························································18
2.4.2 應用：目標跟蹤的非線性/粒子濾波·······················································20
2.4.3 SMC 方法框架總結·········································································23
2.5 應用：利用SMC 方法進行光線追蹤·······················································24
2.6 在重要性采樣中保持樣本多樣性···························································25
2.6.1 基本方法····················································································25
2.6.2 Parzen 窗討論··············································································28
2.7 蒙特卡羅樹搜索················································································29
2.7.1 純蒙特卡羅樹搜索··········································································30
2.7.2 AlphaGo ·····················································································32
2.8 本章練習·························································································33
本章參考文獻··························································································35
第3 章 馬爾可夫鏈蒙特卡羅方法基礎·······························································36
3.1 引言·······························································································36
蒙特卡羅方法與人工智能
·X ·
3.2 馬爾可夫鏈基礎················································································37
3.3 轉移矩陣的拓撲：連通與周期······························································38
3.4 Perron-Frobenius 定理··········································································41
3.5 收斂性度量······················································································42
3.6 連續或異構狀態空間中的馬爾可夫鏈·····················································44
3.7 各態遍歷性定理················································································45
3.8 通過模擬退火進行MCMC 優化·····························································46
3.9 本章練習·························································································49
本章參考文獻··························································································51
第4 章 Metropolis 算法及其變體······································································52
4.1 引言·······························································································52
4.2 Metropolis-Hastings 算法······································································52
4.2.1 原始Metropolis-Hastings 算法······························································53
4.2.2 Metropolis-Hastings 算法的另一形式·······················································54
4.2.3 其他接受概率設計··········································································55
4.2.4 Metropolis 算法設計中的關鍵問題·······························4
展開全部
蒙特卡羅方法與人工智能 作者簡介
朱松純，1996年獲得哈佛大學計算機科學博士學位，現任北京通用人工智能研究院院長、北京大學人工智能研究院院長、北京大學講席教授、清華大學基礎科學講席教授；曾任美國加州大學洛杉磯分校（UCLA）統計學與計算機科學教授，加州大學洛杉磯分校視覺、認知、學習與自主機器人中心主任。 他長期致力于為視覺和智能探尋一個統一的統計與計算框架：包括作為學習與推理的統一表達和數字蒙特卡羅方法的時空因果與或圖（STC-AOG）。他在計算機視覺、統計學習、認知、人工智能和自主機器人領域發表了400多篇學術論文。他曾獲得了多項榮譽，2003年因圖像解析的工作成就獲馬爾獎，1999年因紋理建模、2007年因物體建模兩次獲得馬爾獎提名。2001 年，他獲得了NSF青年科學家獎、ONR青年研究員獎和斯隆獎。因為在視覺模式的概念化、建模、學習和推理的統一基礎方面的貢獻，他2008年獲得了國際模式識別協會授予的J.K. Aggarwal獎。2013 年，他關于圖像分割的論文獲得了亥姆霍茲獎（Helmholtz Test-of-Time Award）。2017年，他因生命度建模工作獲國際認知學會計算建模獎。2011年，他當選IEEE Fellow。他兩次擔任國際計算機視覺與模式識別大會（CVPR 2012，2019）主席。作為項目負責人，他領導了多個ONR MURI和DARPA團隊，從事統一數學框架下的場景和事件理解以及認知機器人的工作。朱松純，1996年獲得哈佛大學計算機科學博士學位，現任北京通用人工智能研究院院長、北京大學人工智能研究院院長、北京大學講席教授、清華大學基礎科學講席教授；曾任美國加州大學洛杉磯分校（UCLA）統計學與計算機科學教授，加州大學洛杉磯分校視覺、認知、學習與自主機器人中心主任。 他長期致力于為視覺和智能探尋一個統一的統計與計算框架：包括作為學習與推理的統一表達和數字蒙特卡羅方法的時空因果與或圖（STC-AOG）。他在計算機視覺、統計學習、認知、人工智能和自主機器人領域發表了400多篇學術論文。他曾獲得了多項榮譽，2003年因圖像解析的工作成就獲馬爾獎，1999年因紋理建模、2007年因物體建模兩次獲得馬爾獎提名。2001 年，他獲得了NSF青年科學家獎、ONR青年研究員獎和斯隆獎。因為在視覺模式的概念化、建模、學習和推理的統一基礎方面的貢獻，他2008年獲得了國際模式識別協會授予的J.K. Aggarwal獎。2013 年，他關于圖像分割的論文獲得了亥姆霍茲獎（Helmholtz Test-of-Time Award）。2017年，他因生命度建模工作獲國際認知學會計算建模獎。2011年，他當選IEEE Fellow。他兩次擔任國際計算機視覺與模式識別大會（CVPR 2012，2019）主席。作為項目負責人，他領導了多個ONR MURI和DARPA團隊，從事統一數學框架下的場景和事件理解以及認知機器人的工作。
巴布·艾俊，2000 年獲得俄亥俄州立大學數學博士學位，2005 年獲得加州大學洛杉磯分校計算機科學博士學位（師從朱松純博士）。2005年至2007年，他在西門子研究院從事醫學成像研究工作，從開始擔任研究科學家到后來升任項目經理。由于在邊緣空間學習方面的工作成就，他與西門子的合作者獲得了2011年Thomas A. Edison專利獎。2007年，他加入佛羅里達州立大學統計系，從助理教授到副教授，再到2019年擔任教授。他發表了70多篇關于計算機視覺、機器學習和醫學成像方面的論文，并擁有超過25項與醫學成像和圖像去噪相關的專利。
魏平，西安交通大學人工智能學院教授、博士生導師，人工智能學院副院長，國家級青年人才，陜西高校青年創新團隊（自主智能系統）帶頭人，西安交通大學“青年拔尖人才支持計劃”A類入選者。西安交通大學學士、博士學位，美國加州大學洛杉磯分校（UCLA）博士后、聯合培養博士。研究領域包括計算機視覺、機器學習、智能系統等。主持國家自然科學基金項目、國家重點研發計劃子課題等科研項目十余項，作為骨干成員參與國家自然科學基金重大科學研究計劃等課題多項。在TPAMI、CVPR、ICCV、ACM MM、AAAI、IJCAI等國際權威期刊和會議發表學術論文多篇，是十余個國際著名期刊和會議審稿人。擔任中國自動化學會網聯智能專委會副主任委員、中國圖象圖形學學會機器視覺專委會委員。
書友推薦
- >
伯納黛特,你要去哪(2021新版)
- >
隨園食單
- >
名家帶你讀魯迅:朝花夕拾
- >
新文學天穹兩巨星--魯迅與胡適/紅燭學術叢書(紅燭學術叢書)
- >
名家帶你讀魯迅:故事新編
- >
唐代進士錄
- >
羅庸西南聯大授課錄
- >
月亮虎
本類暢銷
