Conferences, Lectures, & Seminars
Events for March
-
NL Seminar- Multi-site genetic analysis of the brain’s white matter: ENIGMA-DTI
Fri, Mar 06, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Neda Jahanshad, (USC/ISI)
Talk Title: Multi-site genetic analysis of the brain’s white matter: ENIGMA-DTI
Series: Natural Language Seminar
Abstract: The functioning regions of the brain are connected through a complex network of fibers, described by the brain’s white matter. Non-invasive imaging using MRI-based diffusion imaging can help capture important characteristics of the connections by describing the strength and directionality profile of water diffusion along white matter fibers. Variability in these connections have been noted in many neurological, degenerative, and psychiatric disorders where ultimately information transfer from on brain region to the other may be weakened or completely compromised. To discover genetic risk factors for altered connectivity and common genetic variants which put the brain at subtle risk for weakened connections, we find power in sample size and pool multiple datasets from around the world to determine common effects in all populations. However, there is no standard method for acquiring diffusion images and standardizing measures across datasets is an ongoing challenge. The Enhancing Neuro Imaging Genetics through Meta Analysis group on Diffusion Tensor Imaging has established a set of basic protocols to overcome a portion of these challenges, which I will describe, along with works-in-progress to tackle additional obstacles to reveal critical details of the brains network.
Biography: Neda Jahanshad is an assistant professor of Neurology at USC in the Imaging Genetics Center at ISI. She received her PhD in Biomedical Engineering at UCLA in 2012 where she worked on optimizing diffusion imaging protocols to map structural brain connections in large populations. She has since extended the work to explore methods of pooling such imaging data from across the world and determine genetic and environmental contributions to the connectivity of the brain and determine how these effects vary across the lifespan. She is coordinating one of the largest studies of the brain's white matter through the ENIGMA Consortium http://enigma.ini.usc.edu.
Host: Nima Pourdamghani and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Flr Conf Rm # 689, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
Creating Love through Science
Fri, Mar 20, 2015 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jon Morra, Ph.D., Principal Machine Learning Engineer at eHarmony
Talk Title: Creating Love through Science
Series: AISeminar
Abstract: eHarmony has been creating successful matches for over 15 years. Over that time, our processes have grown in complexity from handmade linear functions to very complex multi-stage pipelines involving some of the latest techniques in data processing, data mining, and machine learning. In this talk I will go over our current data pipeline and highlight recent changes, including the addition of image processing and contextual bandit learning to help improve users' experience on our site. I will also touch upon the future of both our machine learning pipeline and algorithm selection at eHarmony.
Biography: Jon Morra, Ph.D., is a Principal Machine Learning Engineer at eHarmony. His work focuses on eHarmony's machine learning pipeline, including feature extraction, model creation, and data analysis in addition to contributing to the eHarmony engineering infrastructure. Before eHarmony, he co-founded a medical imaging company focused on image segmentation for therapy planning in radiation oncology and developed a novel image segmentation algorithm that was able to find various regions of interest in multi modality imaging environments. Jon has also spent time writing PACS software and developing Ruby on Rails techniques for radiation safety. He received his B.S. in Biomedical Engineering from Johns Hopkins University and his M.S. and Ph.D. in Biomedical Engineering from UCLA.
Host: Ashish Vaswani
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=89ba5d5ed8c640d4aff1b850b308173c1dLocation: Information Science Institute (ISI) - 1135
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=89ba5d5ed8c640d4aff1b850b308173c1d
Audiences: Everyone Is Invited
Contact: Alma Nava / Information Sciences Institute
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
NL Seminar-Multitask Word Alignment with Random-Walk Regularizers
Fri, Mar 20, 2015 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Tomer Levinboim, Notre Dame University
Talk Title: Multitask Word Alignment with Random-Walk Regularizers
Series: Natural Language Seminar
Abstract: Suppose we translate a word from English to French and back. Should we get the original English word? That is, is translation invertible? Alternatively, suppose we translate an English word e to Spanish and then from Spanish to French, obtaining a word f. Should e-f be a valid entry in an English-French dictionary? That is, is translation transitive? Intuitively, if translation is done carefully, we expect to answer both these questions with "Yes, with high probability". In this talk, I will discuss how to formulate our intuition about invertibility/transitivity with random-walks, using translation probability distributions. I will then present two random-walk based regularization techniques that we recently used in a multitask word alignment setting: (1) Model Invertibility Regularization (MIR) - a concave regularizer for bi-directional models which can be applied even without parallel data. (2) Triangulation based Dirichlet prior - a method that capitalizes on parallel data with a pivot language, to construct and learn better translation priors. This talk is based on joint work with Prof. David Chiang (ND) and Dr. Ashish Vaswani (ISI).
Biography: Tomer Levinboim is a PhD student at the University of Notre Dame, working with Prof. David Chiang on developing machine learning techniques for improving machine translation and NLP of low resource languages. He is generously hosted by Kevin Knight at USC/ISI.
Host: Nima Pourdamghani and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Flr Conf Rm # 689, Marina Del Rey
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
