archive-edu.com » EDU » C » COLUMBIA.EDU

Total: 442

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Courses related to Machine Learning
    COMS 4772 6772 Advanced Machine Learning Spring 2010 COMS 4771 Machine Learning Fall 2009 COMS 4772 6772 Advanced Machine Learning Spring 2009 COMS 4771 Machine Learning Fall 2008 COMS 4772 6772 Advanced Machine Learning Spring 2008 COMS 4771 Machine Learning Fall 2007 COMS 4772 6772 Advanced Machine Learning Perception Spring 2007 COMS 6998 4 Learning and Empirical Inference COMS 4771 Machine Learning Fall 2006 COMS 4995 6772 Advanced Machine Learning

    Original URL path: http://www.cs.columbia.edu/learning/courses.html (2016-02-17)
    Open archived version from archive


  • Machine Learning Reading Group Meetings at Columbia
    the difficulty of objectively evaluating how well members of a given a pathway or functional class of interest Gene Set are represented in the markers list To address this problem we introduce a statistical methodology called Gene Set Enrichment Analysis GSEA for determining whether a given Gene Set is over represented or enriched in a Gene List of markers ordered by their correlation with a phenotype or class distinction of interest The method is based upon a score computed as the maximum deviation of a random walk in the same spirit as the Kolmogorov Smirnov statistic and uses permutation testing to assess significance When multiple Gene Sets are tested simultaneously we propose two approaches to address the multiplicity Validation GSEA which controls the Familywise error rate FWER and Discovery GSEA which controls the False Discovery rate FDR The utility of this procedure will be illustrated on two biological problems validating a mouse model of lung cancer and finding chromosomal dislocations for myeloid leukemia April 2 2004 Blei Griffiths Jordan and Tenenbaum Hierarchical Topic Models and the Nested Chinese Restaurant Process Risi presenting Slides ps pdf March 25 2004 Naftali Tishby The Hebrew University Efficient data representations that preserve relevant information A new look at Shannon s Information Theory 11 00am Interschool Lab In this talk I will take a new look at Shannon s Information theory from the Machine Learning perspective I will argue that Shannon s theory provides a compelling mechanism for quantifying the fundamental tradeoff between complexity and accuracy by unifying the source and channel coding theorems into one principle which I call the Information Bottleneck IB This unified view of the coding theorems can shed new light on the question of relevant data representation and suggests new algorithms for extracting such representations from co occurrence statistics It also provides new ways of thinking about neural coding and neural data analysis When applied to the analysis of human language it reveals new possibly universal scaling law that may reflect the way words are acquired in natural languages The IB principle has new interesting extensions that deal with multivariate data using Graphical models and multi information allow adding irrelevant side information and extract nonlinear continuous dimension reduction that preserve information SDR I will describe some of those extensions as time allows More information and many related papers can be found at http www cs huji ac il labs learning Papers IBM list html March 12 2004 Brendan J Frey A Principled and Computationally Efficient Approach to Visual and Auditory Scene Analysis 11 00am Interschool Lab Scene analysis is currently the most exciting problem to work on in sensory processing Scene analysis entails decomposing sensory inputs into a combinatorial explanation that can be used to predict new inputs The problem is old and can be traced back to Helmholtz and more fuzzily to the ancient Greeks who thought that fire etc was the combinatorial explanation However only recently do we have 1 Efficient algorithms that turn exponential time combinatorial inference and learning algorithms into linear time approximate algorithms and 2 Fast computers that can process sensory data repeatedly and quickly enough that grad students stick around to look at the results In this talk I ll describe research on visual and auditory scene analysis being done in my group at the University of Toronto PSI Lab using graphical models and efficient approximate inference algorithms The focus will be on the generative modeling approach and why this approach holds the most promise for solving the problem of sensory scene analysis For serious reading check out the following tutorial paper http www psi toronto edu frey stuff tutorial ps gz For fun videos audio clips gene expression array results etc see the web pages of Nebojsa Jojic my postdocs Romer Rosales Quaid Morris and my current students Kannan Achan Anitha Kannan Chris Pal March 5 2004 John Langford The Method of Reduction in Machine Learning Reductions transform a solver for one domain into a solver for another domain I will discuss a general framework for analyzing reductions between learning domains which captures Boosting ECOC and other well known algorithms I will also present new algorithmic reductions and empirical tests of their performance February 27 2004 Yoav Freund Robert E Schapire Yoram Singer Manfred K Warmuth Using and combining predictors that specialize Ray presenting February 6 2004 Denis V Chigirev William S Bialek Optimal Manifold Representation of Data An Information Theoretic Approach Andy presenting January 30 2004 Vishy SVN Vishwanathan 2 30pm in CEPSR 6LE5 We present Hilbert space embeddings of dynamical systems and embeddings generated via dynamical systems This is achieved by following the behavioural framework invented by Willems namely by comparing trajectories of states As important special cases we recover the diffusion kernels of Kondor and Lafferty generalised versions of directed graph kernels of Gartner novel kernels on matrices and new similarity measures on Markov Models We show applications of our method to Dynamical texture recognition problems from computer vision January 27 2004 Eleazar Eskin The Homology Kernel A Biological Motivated Sequence Embedding 4 30pm in CS Lounge Many recent techniques in learning over biological sequences implicitly embed sequences into a Euclidean space in order to take advantage of strong margin based learning algorithms However these embeddings often do not take advantage of the rich biological intuitions that have motivated development of Hidden Markov Model style biological sequence models and have lead to great successes in computational biology In this talk we present a new biological motivated sequence embedding We discuss several of the formal properties of the embedding include its connection to local sequence alignment One of the key features of the embedding is that a sequence is embedded along with its homologues or neighboring sequences The distance between two sequences is defined by the distance between close neighbors of the sequences We demonstrate application of the embedding to several applications We apply the embedding to learning protein secondary structure and protein family classification We also show how the embedding

    Original URL path: http://www.cs.columbia.edu/learning/meetings.html (2016-02-17)
    Open archived version from archive

  • Links
    Intelligence and Statistics AISTAT Uncertainty and Artificial Intelligence UAI Conference on Learning Theory COLT European Conference on Machine Learning ECML International Conference on Machine Learning and Applications ICMLA As well as these vision conferences occasionaly Computer Vision and Pattern Recognition CVPR International Conference on Computer Vision ICCV European Conference on Computer Vision ECCV The main journals we are interested in include Machine Learning MLJ Journal of Machine Learning Research JMLR

    Original URL path: http://www.cs.columbia.edu/learning/links.html (2016-02-17)
    Open archived version from archive


  • Photo Denise Applewhite

    Original URL path: http://www.cs.columbia.edu/~blei/blei-hi-res.html (2016-02-17)
    Open archived version from archive

  • David M. Blei
    I wrote a general introduction to topic modeling John Lafferty and I wrote a more technical review paper about this field Here are slides from some of my recent talks about topic modeling Probabilistic Topic Models 2012 ICML Tutorial Probabilistic Topic Models 2012 Machine Learning Summer School 211 slides Probabilistic Topic Models Origins and Challenges 2013 Topic Modeling Workshop at NIPS Here is a video from a talk on dynamic

    Original URL path: http://www.cs.columbia.edu/~blei/topicmodeling.html (2016-02-17)
    Open archived version from archive

  • David M. Blei
    of graphical models Fall 2015 STAT CS 6998 4 Truth in data Spring 2015 STAT CS 6509 Foundations of graphical models Fall 2014 COS424 Interacting with data Spring 2014 COS597A Advanced methods in probabilistic modeling Fall 2013 COS424 Interacting with data Spring 2012 COS597C Advanced methods in probabilistic modeling Fall 2011 COS513 Foundations of probabilistic modeling Fall 2010 COS597A Truth in data Fall 2009 COS513 Foundations of probabilistic modeling Spring

    Original URL path: http://www.cs.columbia.edu/~blei/courses.html (2016-02-17)
    Open archived version from archive

  • David M. Blei
    inference nbsp International Conference on Machine Learning 2012 nbsp PDF Code A Chaney and D Blei nbsp Visualizing topic models nbsp International AAAI Conference on Social Media and Weblogs 2012 nbsp PDF J Paisley D Blei and M Jordan nbsp Stick breaking beta processes and the Poisson process nbsp Artificial Intelligence and Statistics 2012 nbsp PDF S Gershman and D Blei nbsp A tutorial on Bayesian nonparametric models nbsp Journal of Mathematical Psychology 56 1 12 2012 nbsp PDF 2011 S Ghosh A Ungureunu E Sudderth and D Blei nbsp Spatial distance dependent Chinese restaurant processes for image segmentation nbsp Neural Information Processing Systems 2011 nbsp PDF D Blei and P Frazier nbsp Distance dependent Chinese restaurant processes nbsp Journal of Machine Learning Reseach 12 2461 2488 2011 nbsp PDF Code L Hannah D Blei and W Powell nbsp Dirichlet process mixtures of generalized linear models nbsp Journal of Machine Learning Research 12 1923 1953 nbsp PDF C Wang and D Blei nbsp Collaborative topic modeling for recommending scientific articles Knowledge Discovery and Data Mining 2011 nbsp Best Student Paper Award nbsp PDF Code and Demo D Mimno and D Blei nbsp Bayesian checking of topic models nbsp Empirical Methods in Natural Language Processing 2011 nbsp PDF S Gershman D Blei F Pereira and K Norman nbsp A topographic latent source model for fMRI data nbsp NeuroImage 57 89 100 2011 J Paisley L Carin and D Blei nbsp Variational inference for stick breaking beta processes nbsp International Conference on Machine Learning 2011 nbsp PDF S Gerrish and D Blei nbsp Predicting legislative roll calls from text nbsp International Conference on Machine Learning 2011 nbsp Distinguished Application Paper Award nbsp PDF J Paisley C Wang and D Blei nbsp The discrete infinite logistic normal distribution for mixed membership modeling nbsp Artificial Intelligence and Statistics 2011 nbsp Notable Paper Award nbsp PDF C Code Matlab C Wang J Paisley and D Blei nbsp Online variational inference for the hierarchical Dirichlet process nbsp Artificial Intelligence and Statistics 2011 PDF Code 2010 M Hoffman D Blei and F Bach nbsp Online learning for latent Dirichlet allocation nbsp Neural Information Processing Systems 2010 nbsp PDF Supplement Code L Hannah W Powell and D Blei nbsp Nonparametric density estimation for stochastic optimization with an observable state variable nbsp Neural Information Processing Systems 2010 nbsp PDF Supplement Long paper J Chang and D Blei nbsp Hierarchical relational models for document networks nbsp Annals of Applied Statistics 4 1 124 150 2010 nbsp PDF Code D Blei and P Frazier nbsp Distance dependent Chinese restaurant processes nbsp International Conference on Machine Learning 2010 nbsp PDF Long paper Code S Gerrish and D Blei nbsp A language based approach to measuring scholarly impact nbsp International Conference on Machine Learning 2010 nbsp PDF M Hoffman D Blei and P Cook nbsp Bayesian nonparametric matrix factorization for recorded music nbsp International Conference on Machine Learning 2010 nbsp PDF S Williamson C Wang K Heller and D Blei nbsp The IBP

    Original URL path: http://www.cs.columbia.edu/~blei/publications.html (2016-02-17)
    Open archived version from archive

  • index.html
    prerequisite course is Foundations of Graphical Models and you should be comfortable with its material Specifically you should be able to write down a new model where each complete conditional is in the exponential family derive and implement an approximate inference algorithm for the model and understand how to interpret its results You should also be fluent in the semantics of graphical models Finally note this is a seminar It

    Original URL path: http://www.cs.columbia.edu/~blei/seminar/2016_discrete_data/index.html (2016-02-17)
    Open archived version from archive