VideoLectures

Predavanje 13 January 22, 2011

VideoLectures

Institutional Perspectives on Storage January 22, 2011 European archivists grapple with the legal obligations, civic responsibilities and future prospects of their collections, which, thanks to the Internet and other new technologies, are ...

VideoLectures

Phoneme Recognition with Large Hierarchical ... January 15, 2011 Automatic speech recognition has gradually improved over the years, but the reliable recognition of unconstrained speech is still not within reach. In order to achieve a breakthrough, many ...

VideoLectures

Information-theoretic lower bounds on the ... January 15, 2011 Relative to the large literature on upper bounds on complexity of convex optimization, lesser attention has been paid to the fundamental hardness of these problems. Recent years have seen a surge ...

VideoLectures

Robust PCA and Collaborative Filtering: ... January 15, 2011 Principal Component Analysis is one of the most widely used techniques for dimensionality reduction. Nevertheless, it is plagued by sensitivity to outliers; finding robust analogs, particularly ...

VideoLectures

The Multidimensional Wisdom of Crowds January 15, 2011 Distributing labeling tasks among hundreds or thousands of annotators is an increasingly important method for annotating large datasets. We present a method for estimating the underlying value ...

VideoLectures

Multiple Kernel Learning for Efficient ... January 15, 2011 The Conformal Predictions framework is a recent development in machine learning to associate reliable measures of confidence with results in classification and regression. This framework is ...

VideoLectures

Parallel Online Learning January 15, 2011

VideoLectures

The Learning Behind the Gmail Priority Inbox January 15, 2011

VideoLectures

Distributed Markov chain Monte Carlo January 15, 2011 We consider the design of Markov chain Monte Carlo (MCMC) methods for large-scale, distributed, heterogeneous compute facilities, with a focus on synthesising sample sets across multiple runs ...

VideoLectures

Building Heterogeneous Platforms for ... January 15, 2011

VideoLectures

Linear Complementarity for Regularized Policy ... January 15, 2011 Recent work in reinforcement learning has emphasized the power of L1 regularization to perform feature selection and prevent overfitting. We propose formulating the L1 regularized linear fixed ...

VideoLectures

MapReduce/Bigtable for Distributed Optimization January 15, 2011 For large data it can be very time consuming to run gradient based optimizat ion,for example to minimize the log-likelihood for maximum entropy models.Distributed methods are therefore appealing ...

VideoLectures

Lecture 19 - Biomechanics and Orthopedics (cont.) January 15, 2011 Professor Saltzman begins the lecture with discussion of the importance of motion for the survival and propagation of any living species. He presents the different modes of motion, taking first ...

VideoLectures

Efficient space-variant blind deconvolution January 14, 2011 Blur in photos due to camera shake, blur in astronomical image sequences due to atmospheric turbulence, and blur in magnetic resonance imaging sequences due to object motion are examples of blur ...

VideoLectures

Mixing sum-product and max-product type ... January 14, 2011

VideoLectures

A Dirty Model for Multi-task Learning January 14, 2011 We consider the multiple linear regression problem, in a setting where some of the set of relevant features could be shared across the tasks. A lot of recent research has studied the use of L1 Lq ...

VideoLectures

Linear Algebra and Machine Learning of Large ... January 14, 2011 Very large informatics graphs such as large social and information networks typically have properties that render many popular machine learning and data analysis tools largely inappropriate. While ...

VideoLectures

Averaging algorithms and distributed optimization January 14, 2011 In distributed averaging and consensus algorithms, processors exchange and update certain values (or "estimates", or "opinions") by forming a local average with the values of their neighbors. ...

VideoLectures

An Incremental Subgradient Algorithm for ... January 14, 2011 We present an incremental subgradient algorithm for approximate computation of maximum-a-posteriori (MAP) states in cyclic graphical models. Its most striking property is its immense simplicity: ...