Select a calendar:
Filter April Events by Event Type:
SUNMONTUEWEDTHUFRISAT
University Calendar
Events for April
-
Last Day to Drop a Spring 2005 Class With a W
Fri, Apr 08, 2005
Viterbi School of Engineering Student Affairs
University Calendar
Audiences: Undergraduate and Graduate Students
Contact: Monica De Los Santos
-
Noninvasive Functional Imaging in Humans and Mice
Fri, Apr 22, 2005 @ 10:30 AM - 11:30 AM
Ming Hsieh Department of Electrical and Computer Engineering
University Calendar
"Noninvasive Functional Imaging in Humans and Mice "Felix Darvas
USC (SIPI)Host: Prof. Richard Leahy (leahy@sipi.usc.edu)AbstractMagnetoencephalography (MEG) and electroencephalography (EEG) provide a unique window on the human brain on a millisecond time scale. Both modalities measure the electromagnetic signals produced by electrical activity in the brain non-invasively. The analysis of cortical activity from MEG and EEG requires the solution of an inverse problem and the associated forward problem. The presentation will introduce basic aspects of the forward and inverse problem and will give a detailed description of two applications which address the solution of the forward problem by means of a generic surrogate head model and the statistical evaluation of the inverse solution. Practical applications of the two methods will be demonstrated by the analysis of two experiments, a somatotopic mapping of the digits in healthy human subjects using MEG and measurement of visual evoked potentials (VEP) in blind subjects with a retinal implant.Another imaging modality, optical bioluminescence tomography, which makes use of similar principles, will also be presented. This image modality has its primary application in the molecular imaging domain in small animals, i.e. in mice. Aspects of forward photon flux forward models and the novel approach of hyperspectral optical tomography will be discussed and preliminary results of in-vivo application of the method in tumor mice will be shown.BiographyUndergraduate studies of physics at the Ludwig-Maximilians Universität München (LMU) and the Rheinisch-Westfälische Technische Hochschule (RWTH) AAchen. Graduated in 1998 with degree Diplom-Physiker (MS physics). Graduate studies from 1998 to 2002 at the RWTH Aachen in the field of biomedical imaging, thesis on time dependent current density reconstruction from EEG data. Postdoctoral research associate at Signal and Image Processing Institute (SIPI) at the University of Southern California from 2002- present. Current work on forward modeling and source analysis in MEG/EEG and optical imaging.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Regina Morton
-
Last Day of Classes
Fri, Apr 29, 2005
Viterbi School of Engineering Student Affairs
University Calendar
Audiences: Undergraduate and Graduate Students
Contact: Monica De Los Santos
-
Speech, Language, and Graphical Models: Representation and Computation
Fri, Apr 29, 2005 @ 02:00 AM - 03:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
University Calendar
Speech, Language, and Graphical Models: Representation and ComputationJeff A. Bilmes
Department of Electrical Engineering
University of Washington, SeattleAbstractGraphical models are a general statistical abstraction that can represent the inherent uncertainty within many scientific and engineering tasks. Recent research has indicated that they hold great promise for advancing speech and language processing. These time series, however, have properties that introduce unique and challenging research problems. The first part of this talk will present a variety of graph features and structures that solve many problems in speech and language. Two styles of structure determination are of particular interest: those whose goal is to represent knowledge, and those that are determined in a data-driven fashion specifically to reduce errors. Next, we will outline the computational challenges in applying this framework to speech and language, and describe our solutions. This includes dynamic graph triangulation methods, dynamic exact and approximate probabilistic inference methods, and a host of others, thereby making tractable computing with an enormous number of system variables.BiographyJeff A. Bilmes is an Assistant Professor in the Department of Electrical Engineering at the University of Washington, Seattle (and adjunct in Linguistics and also in Computer Science and Engineering). He co-founded the Signal, Speech, and Language Interpretation Laboratory at the University. He received a masters degree from MIT, and a Ph.D. in Computer Science at the University of California, Berkeley. Jeff is the author of the graphical models toolkit (GMTK), and has done much research on both structure learning of and fast probabilistic inference in dynamic Graphical models (DGMs). Jeff was a leader of the 2001 Johns Hopkins summer workshop team applying graphical models to speech and language, and has continued to lead in the speech/language community in this endeavor. His primary research lies in statistical graphical models, speech, language and time series processing, human-computer interaction, probabilistic machine learning, and high-performance computing. He was a general co-chair for IEEE Automatic Speech Recognition and Understanding 2003, and is a member of IEEE, ACM, and ACL. He is a 2001 CRA Digital-Government Research Fellow, and is a 2001 recipient of the NSF CAREER award. Additional information is available at: http://ssli.ee.washington.edu/~bilmesDate: April 29, 2005 (Friday)
Time: 2:00 pm
Location: EEB 248
Host: Shri Narayanan, EE-Systems (SIPI)
Contact: shri@sipi.usc.edu (x 06432)
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Regina Morton
-
Factored Language Models
Fri, Apr 29, 2005 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
University Calendar
"Factored Language Models"Katrin Kirchhoff
Department of Electrical Engineering
University of Washington, SeattleAbstractLanguage modeling for large-vocabulary automatic speech recognition is often faced with the problem of sparse training data. This is a particularly severe problem for languages with rich morphology, which results in a high vocabulary growth rate and a large number of unseen word contexts. One way of addressing data sparsity is to adopt a feature-based word representation, where words are not considered atomic units but feature vectors consisting of more fine-grained modeling units. This representation can be used to develop more robust language models (so-called factored language models) that are able to share training data across words. I will describe how to develop factored word representations and the resulting probability estimation methods and present results on language modeling for both speech recognition and machine translations.BiographyKatrin Kirchhoff studied Linguistics and Computer Science at the Universities of Bielefeld (Germany) and Edinburgh (UK) and obtained her PhD in Computer Science from the University of Bielefeld in 1999. Since then she has been a Research Assistant Professor in the Electrical Engineering Department at the University of Washington. Her main research interests are speech recognition, language modeling, multilingual speech processing, and machine learning.Date: April 29, 2005 (Friday)
Time: 10:00 am
Host: Shri Narayanan, EE-Systems (SIPI)
Contact: shri@sipi.usc.edu (x 06432)
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Regina Morton
-
2005 Engineering Awards Luncheon
Fri, Apr 29, 2005 @ 11:00 AM
Viterbi School of Engineering Alumni
University Calendar
2005 Annual Engineering Awards Luncheon honoring:Yang Ho Cho
Daniel J. Epstein Engineering Management AwardKenneth C. Dahlberg
Mark A. Stevens Distinguished Alumni AwardMichael B. Pursley
Distinguished Alumni Award in AcademiaJuan Enriquez
Special Guest Speaker
Author of "As the Future Catches You: How Genomics and Other forces are Changing Your Life, Work, Health and Wealth"For more information or to RSVP, please call the External Relations Office at (213) 740-2502.Location: The Westin Century Plaza Hotel - Olympic Ballroom (2025 Avenue of the Stars, Los Angeles)
Audiences: Alumni
Contact: Mayne Joyce
-
Registration Deadline for the PhD Screening Exam
Fri, Apr 29, 2005 @ 12:00 PM
Alfred E. Mann Department of Biomedical Engineering
University Calendar
You will need to register for the exam with Adam Wyatt. Please fill out this form return it to Adam Wyatt. Please make sure you fill out all sections completely and accurately. He will be checking your grades before the exam for accuracy. The registration deadline for the screening exam will be 12:00pm on April 29, 2005. There will be no late forms accepted!Please click HERE for more details.
Audiences: Graduate/Department Only
Contact: Darryl Hwang
