BestTechVideos: Category Google Videos

An Overview of High Performance Computing and Challenges for the Future

scoundrel — Fri, 25 Apr 2008 01:40:50 GMT

Google Tech Talks
January, 25 2008

ABSTRACT

In this talk we examine how high performance computing has changed over the last 10-year and look toward the future in terms of trends. These changes have had and will continue to have a major impact on our software. A new generation of software libraries and algorithms are needed for the effective and reliable use of (wide area) dynamic, distributed and parallel environments. Some of the software and algorithm challenges have already been encountered, such as management of communication and memory hierarchies through a combination of compile--time and run--time techniques, but the increased scale of computation, depth of memory hierarchies, range of latencies, and increased run--time environment variability will make these problems much harder.

We will focus on the redesign of software to fit multicore architectures.

Speaker: Jack Dongarra
University of Tennessee
Oak Ridge National Laboratory
University of Manchester
Jack Dongarra received a Bachelor of Science in Mathematics from Chicago State University in 1972 and a Master of Science in Computer Science from the Illinois Institute of Technology in 1973. He received his Ph.D. in Applied Mathematics from the University of New Mexico in 1980. He worked at the Argonne National Laboratory until 1989, becoming a senior scientist. He now holds an appointment as University Distinguished Professor of Computer Science in the Electrical Engineering and Computer Science Department at the University of Tennessee, has the position of a Distinguished Research Staff member in the Computer Science and Mathematics Division at Oak Ridge National Laboratory (ORNL), Turing Fellow in the Computer Science and Mathematics Schools at the University of Manchester, and an Adjunct Professor in the Computer Science Department at Rice University.

He specializes in numerical algorithms in linear algebra, parallel computing, the use of advanced-computer architectures, programming methodology, and tools for parallel computers. His research includes the development, testing and documentation of high quality mathematical software. He has contributed to the design and implementation of the following open source software packages and systems: EISPACK, LINPACK, the BLAS, LAPACK, ScaLAPACK, Netlib, PVM, MPI, NetSolve, Top500, ATLAS, and PAPI. He has published approximately 200 articles, papers, reports and technical memoranda and he is coauthor of several books. He was awarded the IEEE Sid Fernbach Award in 2004 for his contributions in the application of high performance computers using innovative approaches. He is a Fellow of the AAAS, ACM, and the IEEE and a member of the National Academy of Engineering.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Companies, Science, Techtalks, Google, Lectures, Math, Computer Science

What Do Those Images Have In Common?

scoundrel — Fri, 25 Apr 2008 01:39:50 GMT

Google Tech Talks
March, 25 2008

ABSTRACT

This talk is about discovering and modeling previously unspecified, recurring themes in a given set of arbitrary images. Given a set of images, each containing frequent occurrences of objects from multiple categories, the goal is to learn a compact model of the categories as well as their relationships, for the purposes of later recognizing/segmenting any occurrences in new images. Categories are not defined by the user. Also, whether and where instances of any categories appear in a specific image is not known. This problem is challenging, since it involves the following unanswered questions. What is an object category? What image properties should be used and how to combine them to discover category occurrences? What is an efficient multicategory representation?

We will examine a methodology, developed during my postdoctoral work at UIUC. Each image is represented by a segmentation tree whose nodes correspond to image regions, segmented at all natural scales present, and edges between tree nodes capture the region embedding. The presence of any categories in the image set is then reflected in the frequent occurrence of similar subtrees within the segmentation trees. Our methodology is designed to: (1) match image trees to find similar subtrees; (2) discover categories by clustering similar subtrees, and use the properties of each cluster to learn the model of the associated category; and (3) learn the grammar of the discovered categories that compactly captures their recursive definitions in terms of other simpler (sub)categories and their relationships (e.g., containment, co- occurrence, and sharing of simple categories by more complex ones). When a new image is encountered, its segmentation tree is matched against the learned grammar to simultaneously recognize and segment all occurrences of the learned categories. This matching also provides a semantic explanation of object recognition in terms of the identified parts along with their spatial relationships.

The aforementioned methodology can also be used for identifying recurring image themes of more general kind. An example is that of extracting the stochastically repeating, elementary parts of image texture (e.g., waterlilies on the water surface, people in a crowd).

This talk will be taped by the engEDU Tech Talks Team.

Speaker: Sinisa Todorovic
Sinisa Todorovic received the joint B.S./M.S. degree with honors in electrical engineering from the University of Belgrade, Serbia, in 1994. From 1994 until 2001, he worked in the communications industry. He received the M.S. and Ph.D. degrees in electrical and computer engineering at the University of Florida, Gainesville, in 2002, and 2005, respectively. Since 2005, he holds the position of Postdoctoral Research Associate in the Beckman Institute at the University of Illinois Urbana-Champaign, where he collaborates with Prof. Narendra Ahuja. Sinisa's main research interests concern computer vision and machine learning, with current focus on unsupervised extraction and representation of visual themes recurring in images. He is the recipient of Jack Neubauer Best Paper Award 2004 for a publication in IEEE Trans. Vehicular Technology, and Outstanding Reviewer Award at the Int. Conf. on Computer Vision (ICCV) 2007. He serves as Associate Editor of Advances in Multimedia.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Companies, Science, Techtalks, Google, Lectures, DSP, Computer Science

KNFB Reader, Talking OCR On Cell Phones

scoundrel — Tue, 15 Apr 2008 20:46:39 GMT

Google Tech Talks
March, 26 2008

ABSTRACT

KNFB Reader, Talking OCR On Cell Phones

www.knfbreader.com

Speaker: James Gashel

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Technologies, Techtalks, Google, Lectures

Decayed MCMC for probabilistic filtering

scoundrel — Tue, 15 Apr 2008 20:46:08 GMT

Google Tech Talks
March, 28 2008

ABSTRACT

Bhaskara M. Marthi - Research Scientist

I will describe an algorithm for probabilistic filtering, the problem of maintaining a probability distribution over the hidden state of a dynamical system given periodic noisy observations. This problem appears in various guises in practice, such as activity monitoring, state estimation, visual tracking, and fault diagnosis. Our algorithm, known as decayed MCMC, scales better than exact methods on many problems, and is less susceptible to losing track of the mode than the popular sequential Monte Carlo or particle filtering methods. Standard Markov chain Monte-Carlo mixing time analyses are insufficient to bound the complexity of our algorithm, and so we extend them to the setting of convergence of a marginal distribution.

Speaker: Dr. Bhaskara M. Marthi - Research Scientist
Dr. Bhaskara Marthi is currently a postdoctoral research associate at MIT, working with Leslie Kaelbling and Tomas Lozano Perez on hierarchical planning and robotic manipulation. He received his PhD in 2006 from the University of California, Berkeley, working with Stuart Russell on reinforcement learning with partial programs, and its application to AI design for large real-time strategy video games. His other interests include probabilistic reasoning, relational and first-order models, and Monte Carlo algorithms.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Science, Techtalks, Google, Lectures, Math, Statistics, Computer Science

Using Java (GWT) with Google App Engine

vojko — Tue, 15 Apr 2008 19:20:13 GMT

Since Google App Engine (GAE) announcement many developers are wondering when/if Google App Engine will support Java. As we already know GAE currently supports only Phyton. Do Java developers have to wait for Java support in GAE? In my opinion, no.

Two parts screencast shows how to run GWT application on Google App Engine.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Web 2.0, AJAX, Google, Java, Python, Screencasts

Scene Discovery by Matrix Factorization

scoundrel — Mon, 07 Apr 2008 22:51:58 GMT

Google Tech Talks
March, 24 2008

ABSTRACT

What constitutes a scene? Defining a meaningful vocabulary for scene discovery is a challenging problem that has important consequences for object recognition. We consider scenes to depict correlated objects and present visual similarity. We introduce a max-margin factorization model that finds a low dimensional subspace with high discriminative power for correlated annotations. We postulate this space should allow us to discover a large number of scenes in unsupervised data; we show scene discrimination results on par with supervised approaches. This model also produces state of the art word prediction results including good
annotation completion.

Speaker: Ali Farhadi
Ali Farhadi is a PhD student in the UIUC Computer Science Department working on computer vision and machine learning under David Forsyth. His interests include image segmentation, transfer learning, scene understanding and human activity recognition.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Broadcasting, Science, Techtalks, Google, Lectures, Math, Computer Science

Movie/Script: Alignment and Parsing of Video and Text Transcription

scoundrel — Mon, 07 Apr 2008 22:51:25 GMT

Google Tech Talks
March, 26 2008

ABSTRACT

Timothee Cour - Research Scientist

Movies and TV are a rich source of highly diverse and complex video of people, objects, actions and locales "in the wild". Harvesting automatically labeled sequences of actions from video would enable creation of large-scale and highly-varied datasets. To enable such collection, we focus on the task of recovering scene structure in movies and TV series for object/person tracking and action retrieval. We present a weakly supervised algorithm that uses the screenplay and closed captions to parse a movie into a hierarchy of shots and scenes. Scene boundaries in the movie are aligned with screenplay scene labels and shots are reordered into a sequence of long continuous tracks or threads which allow for more accurate tracking of people and actions across shot boundaries. Scene segmentation, alignment, and shot threading are formulated as inference in a unified generative model and a novel hierarchical dynamic programming algorithm that can handle alignment and jump-limited reorderings in linear time is introduced. We present quantitative and qualitative results on movie alignment and parsing, and use the recovered structure for tracking and naming of characters as well as retrieval of common actions in several episodes of popular TV series.

If time permits we will also present our recent results on approximate inference with eigenvalue optimization.

Speaker: Timothee Cour - Research Scientist
Timothee Cour is a fifth year PhD student at the University of Pennsylvania, Philadelphia, in Computer Science. He completed his undergraduate education at the Ecole Polytechnique in France, majoring in Computer Science and Applied Mathematics. His research advisor is Prof. Ben Taskar and he also worked closely with Prof. Jianbo Shi.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Science, Techtalks, Google, Lectures, DSP, Computer Science

Optimization for Machine Learning

scoundrel — Mon, 07 Apr 2008 22:50:57 GMT

Google Tech Talks
March, 25 2008

ABSTRACT

S.V.N. Vishwanathan - Research Scientist

Regularized risk minimization is at the heart of many machine learning algorithms. The underlying objective function to be minimized is convex, and often non-smooth. Classical optimization algorithms cannot handle this efficiently. In this talk we present two algorithms for dealing with convex non-smooth objective functions. First, we extend the well known BFGS quasi-Newton algorithm to handle non-smooth

functions. Second, we show how bundle methods can be applied in a machine learning context. We present both theoretical and experimental justification of our algorithms.

Speaker: S.V.N. Vishwanathan - Research Scientist - Zurich
S.V.N Vishwanathan is a principal researcher in the Statistical Machine Learning program, National ICT Australia with an adjunct appointment at the College of Engineering and Computer Science(CECS), Australian National University. I got my Ph.D in 2002 from the Department of Computer Science and Automation (CSA) at the Indian Institute of Science.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Conferences, Companies, Science, Techtalks, Google, Lectures, Computer Science

C++ Stylistics

scoundrel — Wed, 02 Apr 2008 18:02:40 GMT

Google Tech Talks
March, 5 2008

ABSTRACT

Both by accident and by design, C++ supports a number of different styles and approaches to programming. Its evolution from C gives it obvious support for a procedural systems programming style based on C idioms, but past, present and future language support opens up a wealth of other approaches and idioms, including object-oriented programming, generic programming and some elements of functional programming.

This diversity is both a strength and a weakness. It can lead to code that is crisp and well matched to its problem. But it can also lead to code that is at best considered an exercise in groundless post-modernism or, less favorably, an unmaintainable and incoherent mess.

This talk examines some of the styles and approaches, including their key strengths and accidental complexities, as well as consequences of and techniques for combining them.

Speaker: Kevlin Henney
Kevlin Henney is an independent consultant and trainer based in Bristol, UK. Kevlin's work focuses on software architecture, programming languages and development process. He has been a columnist for various magazines and online publications, including SearchSoftwareQuality.com, The Register, C/C++ Users Journal, C++ Report, JavaSpektrum and Java Report. With Frank Buschmann and Doug Schmidt, he is coauthor of two volumes in the Pattern-Oriented Software Architecture series: A Pattern Language for Distributed Computing and On Patterns and Pattern Languages.

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under Development, Science, Techtalks, Google, C and C++, Lectures, Computer Science

KDE4 Release Event

scoundrel — Wed, 02 Apr 2008 18:01:18 GMT

Google Tech Talks
January 18, 2008

ABSTRACT

Celebration of the KDE 4.0 release, a culmination of several years of design, development and testing.

Speaker: Aaron Baalbergen

Read more about this video…

Want to control this feed contents? Sign up here and create your own feed!

Want more on these topics?
Browse the archive of posts filed under OS, Development, Linux, Techtalks, Google, Lectures