COMP 875COMP 875Machine Learning Methods in Image AnalysisWhat the class is about• “Applied” machine learning and statistical methods• Applications are primarily, though not exclusively, to computer vision and medical imagingto computer vision and medical imaging• Students from other research areas are welcome•Exact list of topics to be determined byyou!•Exact list of topics to be determined by you!Who should take this class?• This is meant as an “advanced” graduate course•Ideally you should have taken COMP 665 775•Ideally, you should have taken COMP 665, 775, 776, or Data Mining (or similar courses elsewhere)elsewhere)• You should be comfortable reading and understanding papers in recent conferences such u de sta d g pape s ece t co e e ces sucas CVPR, ICCV, MICCAI, NIPS, ICML, etc.• You should have some experience doing research pgpresentations• If you have questions or doubts about your background, please talk to me after this classWhy Machine Learning?• Image analysis early on: simple tasks, few imagesL. G. Roberts, Machine Perception of Three Dimensional Solids,Ph.D. thesis, MIT Department of Electrical Engineering, 1963.Why Machine Learning?• Image analysis early on: try to program a computer directly using rules and symbolic representationsY. Ohta, T. Kanade, and T. Sakai, “An Analysis System for Scenes Containing objects with Substructures,” Proceedings of the Fourth International Joint Conference on Pattern Recognition, 1978, pp. 752-754.Why Machine Learning?• Today: Lots of data, complex tasksInternet images, Movies, news, sportspersonal photo albumsSurveillance and securityMedical and scientific imagesWhy Machine Learning?• Today: Lots of data, complex tasks• Instead of trying to encode rules directly, learn them from examples of inputs and desired outputsNot Just Image Analysis• Speech recognition• Document analysis• Spam filtering• Computer security• Statistical debugging• Bioinformatics•….Topics (tentative)• Classifiers: linear models, boosting, support vector machines• Kernel methods • Bayesian methods, Expectation Maximization • Random field models • Sampling techniques such as Markov Chain Monte Carlo • Unsupervised learning: density estimation, clustering •Manifold learning and dimensionality reduction•Manifold learning and dimensionality reduction • Distance metric learning •Semi-supervised learningSemisupervised learning • Online and active learning • Sequential inference (i.e., tracking) • Large-scale learningClass requirements• Class format: lectures and student presentations• Grading:• Presentation: 35%• Project: 35%•Participation: 30%Participation: 30%Presentation• You are “professor for a day”: you need to give a one-hour lecture that would be it ti d ibl t llth td tinteresting and accessible to all the students in the class•You are responsible for selecting your own•You are responsible for selecting your own topic and paper(s)• Look at the list of reading materials on the class webpagegpg• Look through recent conference proceedings• Pick a topic of interest based on your own researchPresentation Guidelines• Evaluation criteria• Integration: utilize multiple sources•Critical thinking:separate the essential from the non•Critical thinking: separate the essential from the non-essential; critique the papers you present; think of alternative applications and future research directions•Interactivity:try to involve the rest of the class•Interactivity: try to involve the rest of the class• Structuring the presentationgp• Will depend on your focus• Broadly speaking, you may want to focus either on a particular learning topic or a particular applicationparticular learning topic, or a particular applicationSample Presentation Outline• Introduction• Problem definition •Problem formulation•Problem formulation• Significance•Survey of methods for solving this problemygp• Detailed presentation of one or more specific methods• Discussion• Pluses and minuses of different methods• Compare and contrast different approaches• Ideas for improvement and future research• Alternative applicationspp• Alternative methods for solving the same problem• Connect your topic to other topics discussed earlier in classPresentation Timeline• Reading list: due next Thursday, September 3rd•Preliminary slides:due Monday the week beforePreliminary slides: due Monday the week before your scheduled presentation• Practice meeting: scheduled for the week before gyour presentation• Final slides: due by the end of the day after your yyypresentation•All of the above are part of your presentation gradeAll of the above are part of your presentation grade (35% of total class grade)A note on slides o m st e plicitl credit all so rces•A note on slides: you must explicitly credit all sourcesProject• Your project topic may be the same as your presentation topicN t i d b t k lif i•Not required, but may make your life easier• Two options: implementation or survey paperImplementation• Implement one or more methods from literature• Conduct a comparative evaluation• Implement your own ideas or extensions of existing methods• Deliverable: an “informal” final report and (ibl)ht tti(possibly) a short presentation• Students may collaborate, but each must submit his/her deliverableshis/her deliverables• You can use existing code and/or software, provided you document all your sources and itprovided you document all your sources and it doesn’t make your project trivialSurvey Paper• Comprehensive tutorial, literature review• A “formal” academic paper• Typeset in LaTeX, 10-15 pages (single-spaced, 11pt font)• Must be individualProject timeline (tentative)• Project proposal: due end of September (details to follow)• Progress report (for implementation) or draft paper (for survey, ~5 pages): due end of OctoberFi l tdltd fl•Final report or paper: due last day of class (December 8th)• All of the above are part of your project grade (35% of total class grade)(35% of total class grade)Participation (30% of the grade)• Class attendance, being on time• Answer questions in review sessions at the beginning of class• Be prepared• Read all the material before the class and come up with ~3 questions for discussion• I may call on anyone at any time• Participate in discussions• Send email to me and/or the class