IntroductionSlide 2Speech recognitionTracking and robot localizationEvolutionary biologyModeling sensor dataPlanning under uncertaintyImages and text dataStructured data (text, webpages,…)Slide 10SyllabusPrerequisitesReview SessionsStaffFirst Point of Contact for HWsText BooksGradingHomeworksEnjoy!What are the fundamental questions of graphical models?More details???Where do we start?TodayRandom variableInterpretations of probability – A can of worms!Conditional probabilitiesTwo of the most important rules of the semester: 1. The chain ruleTwo of the most important rules of the semester: 2. Bayes ruleMost important concept: a) IndependenceMost important concept: b) Conditional independenceJoint distribution, MarginalizationMarginalization – The general caseBasic concepts for random variablesConditionally independent random variablesProperties of independenceBayesian networksHandwriting recognitionHandwriting recognition 2Webpage classificationWebpage classification 2Let’s start on BNs…What if variables are independent?Conditional parameterization – two nodesConditional parameterization – three nodesThe naïve Bayes model – Your first real Bayes NetWhat you need to knowNext classIntroductionGraphical Models – 10708Carlos GuestrinCarnegie Mellon UniversitySeptember 8th, 2008Readings:Review: K&F: *2.1*, 2.2, 2.3K&F: 3.110-708 – Carlos Guestrin 20082 One of the most exciting developments in machine learning (knowledge representation, AI, EE, Stats,…) in the last two (or three, or more) decades…My expectations are already high… 10-708 – Carlos Guestrin 20083Speech recognitionHidden Markov models and their generalizations10-708 – Carlos Guestrin 20084Tracking and robot localization[Fox et al.][Funiak et al.]Kalman Filters10-708 – Carlos Guestrin 20085Evolutionary biology[Friedman et al.]Bayesian networks10-708 – Carlos Guestrin 20086Modeling sensor dataUndirected graphical models[Guestrin et al.]10-708 – Carlos Guestrin 20087Planning under uncertaintyF’E’ G’ P’ PeasantFootman Enemy GoldRt t+1TimeAPeasant ABuild AFootman P(F’|F,G,AB,AF)[Guestrin et al.]Dynamic Bayesian networksFactored Markov decision problems10-708 – Carlos Guestrin 20088Images and text data[Barnard et al.]Hierarchical Bayesian models10-708 – Carlos Guestrin 20089Structured data (text, webpages,…)[Koller et al.]Probabilistic relational models10-708 – Carlos Guestrin 200810And manymany many many manymore…10-708 – Carlos Guestrin 200811SyllabusCovers a wide range of Probabilistic Graphical Models topics – from basic to state-of-the-artYou will learn about the methods you heard about:Bayesian networks, Markov networks, factor graphs, conditional random fields, decomposable models, junction trees, parameter learning, structure learning, semantics, exact inference, variable elimination, context-specific independence, approximate inference, sampling, importance sampling, MCMC, Gibbs, variational inference, loopy belief propagation, generalized belief propagation, Kikuchi, Bayesian learning, missing data, EM, Chow-Liu, structure search, IPF for tabular MRFs, Gaussian and hybrid models, discrete and continuous variables, temporal and template models, hidden Markov Models, Forwards-Backwards, Viterbi, Baum-Welch, Kalman filter, linearization, switching Kalman filter, assumed density filtering, DBNs, BK, Relational probabilistic models, Causality,…Covers algorithms, theory and applicationsIt’s going to be fun and hard work 10-708 – Carlos Guestrin 200812Prerequisites10-701 – Machine Learning, especially:Probabilities Distributions, densities, marginalization…Basic statisticsMoments, typical distributions, regression…AlgorithmsDynamic programming, basic data structures, complexity…ProgrammingMatlab will be very usefulWe provide some background, but the class will be fast pacedAbility to deal with “abstract mathematical concepts”10-708 – Carlos Guestrin 200813Review SessionsVery useful!Review materialPresent backgroundAnswer questionsThursdays, 5:00-6:20 in Wean Hall 5409First recitation is this ThursdayReview of probabilities & statisticsSometimes this semester: Especial recitations most likely on Mondays 5:30-7pmCover special topics that we can’t cover in classThese are optional, but you are here to learn… Do we need a Matlab review session?10-708 – Carlos Guestrin 200814StaffTwo Great TAs: Great resource for learning, interact with them!Amr Ahmed <[email protected]>, Dhruv Batra <[email protected]>Administrative AssistantMichelle Martin <[email protected]>, Wean 4619, x8-552710-708 – Carlos Guestrin 200815First Point of Contact for HWsTo facilitate interaction, a TA will be assigned to each homework question – This will be your “first point of contact” for this questionBut, you can always ask any of usFor e-mailing instructors, always use:[email protected]For announcements, subscribe to:[email protected]https://mailman.srv.cs.cmu.edu/mailman/listinfo/10708-announceWe will also use a discussion group:Post your questions, discuss projects, etcBe nice… Don’t give away any answers… http://groups.google.com/group/10708-f0810-708 – Carlos Guestrin 200816Text BooksPrimary: Daphne Koller and Nir Friedman, Structured Probabilistic Models, in preparation. These chapters are part of the course reader. You can purchase one from Michelle Martin Secondary: M. I. Jordan, An Introduction to Probabilistic Graphical Models, in preparation. Copies of selected chapters will be made available.10-708 – Carlos Guestrin 200817Grading5 homeworks (50%)First one goes out next Wednesday!Homeworks are long and hard please, please, please, please, please, please start early!!!Final project (30%)Done individually or in pairsDetails out soonProposals due October 6th Final (20%)Take home, out Dec. 3rdDue Dec. 10th at NOON (hard deadline)10-708 – Carlos Guestrin 200818HomeworksHomeworks are hard, start early Due in the beginning of class3 late days for the semesterAfter late days are used up:Half credit within 48 hoursZero credit after 48 hoursAll homeworks must be handed in, even for zero creditLate homeworks handed in to Michelle Martin, WEH 4619CollaborationYou
View Full Document
Unlocking...