蒙特卡羅方法與人工智能

定　價：￥138.00

作　者：	（美）Adrian Barbu（巴布·艾?。?，Song-Chun Zhu（朱松純）
出版社：	電子工業(yè)出版社
叢編項：
標　簽：	暫缺

購買這本書可以去

當當網(wǎng) (￥103.50)

ISBN：	9787121470202	出版時間：	2024-01-01	包裝：	平裝-膠訂
開本：	16開	頁數(shù)：		字數(shù)：

內(nèi)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(shù)據(jù)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(tǒng)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(yè)界的從業(yè)者閱讀。

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(xiàn)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(tǒng)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(tǒng)一的統(tǒng)計與計算框架：包括作為學習與推理的統(tǒng)一表達和數(shù)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(tǒng)計學習、認知、人工智能和自主機器人領域發(fā)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(tǒng)一基礎方面的貢獻，他2008年獲得了國際模式識別協(xié)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(tǒng)一數(shù)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(shù)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(yī)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(jīng)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(tǒng)計系，從助理教授到副教授，再到2019年擔任教授。他發(fā)表了70多篇關于計算機視覺、機器學習和醫(yī)學成像方面的論文，并擁有超過25項與醫(yī)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(chuàng)新團隊（自主智能系統(tǒng)）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(lián)合培養(yǎng)博士。研究領域包括計算機視覺、機器學習、智能系統(tǒng)等。主持國家自然科學基金項目、國家重點研發(fā)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(fā)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(wǎng)聯(lián)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。

圖書目錄

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(yōu)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(xù)或異構狀態(tài)空間中的馬爾可夫鏈·····················································44
3.7 各態(tài)遍歷性定理················································································45
3.8 通過模擬退火進行MCMC 優(yōu)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