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(chǔ)、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(qū)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(lǐng)域的代表性應(yīng)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(yīng)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(lǐng)域解決更廣泛的問題，同時使這些領(lǐng)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(lǐng)域的教師、學生閱讀和參考，也適合相關(guān)領(lǐng)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(chǔ)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(lǐng)域發(fā)表了400多篇學術(shù)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(chǔ)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(guān)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(lǐng)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(guān)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(guān)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(lǐng)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(quán)威期刊和會議發(fā)表學術(shù)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(wù)·······································································.2
1.3.1 任務(wù)1：采樣和模擬········································································.3
1.3.2 任務(wù)2：通過蒙特卡羅模擬估算未知量···················································.5
1.3.3 任務(wù)3：優(yōu)化和貝葉斯推理································································.7
1.3.4 任務(wù)4：學習和模型估計···································································.8
1.3.5 任務(wù)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(quán)樣本·······································································15
2.4 序貫重要性采樣（SIS） ······································································18
2.4.1 應(yīng)用：表達聚合物生長的自避游走························································18
2.4.2 應(yīng)用：目標跟蹤的非線性/粒子濾波·······················································20
2.4.3 SMC 方法框架總結(jié)·········································································23
2.5 應(yīng)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(chǔ)·······························································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(chǔ)················································································37
3.3 轉(zhuǎn)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(gòu)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(shè)計··········································································55
4.2.4 Metropolis 算法設(shè)計中的關(guān)鍵問題·······························4