Select a calendar:
Filter October Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for October 25, 2018
-
NL Seminar-Conversational Question Answering
Thu, Oct 25, 2018 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Scott Yih, AI2
Talk Title: Conversational Question Answering
Series: Natural Language Seminar
Abstract: Humans seek information in a conversational manner, by asking follow-up questions for additional information based on what they have already learned. In this talk, I will first introduce the task of sequential question answering 1. which aims to fulfill user's information need by answering a series of simple, but interdependent questions regarding a given table. Treating this task as a semantic parsing problem, we developed a policy shaping mechanism that incorporates prior knowledge and an update equation that generalizes three different families of learning algorithms 2. After that, I will then talk briefly about QuAC, a new dataset for Question Answering in Context. QuAC targets the scenario where the information source is unstructured text 3. and thus can be viewed as a conversational machine comprehension task. New, unpublished model ideas will also be discussed.
Biography: Scott Wen-tau Yih is a Principal Research Scientist at Allen Institute for Artificial Intelligence AI2. His research interests include natural language processing, machine learning and information retrieval. Yih received his Ph.D. in computer science at the University of Illinois at Urbana-Champaign. His work on joint inference using integer linear programming ILP has been widely adopted in the NLP community for numerous structured prediction problems. Prior to joining AI2, Yih has spent 12 years at Microsoft Research, working on a variety of projects including email spam filtering, keyword extraction and search & ad relevance. His recent work focuses on continuous representations and neural network models, with applications in knowledge base embedding, semantic parsing and question answering. Yih received the best paper award from CoNLL-2011, an outstanding paper award from ACL-2015 and has served as area co-chairs HLT-NAACL-12, ACL-14, EMNLP-16,17,18, program co-chairs CEAS-09, CoNLL-14 and action associated editors TACL, JAIR in recent years. He is also a co-presenter for several tutorials on topics including Semantic Role Labeling NAACL-HLT-06, AAAI-07, Deep Learning for NLP SLT-14, NAACL-HLT-15, IJCAI-16, NLP for Precision Medicine ACL-17, AAAI-18.
Host: Xusen Yin
More Info: http://nlg.isi.edu/nl-seminar/
Webcast: https://bluejeans.com/s/jIoDx/Location: Information Science Institute (ISI) - 6th Floor Conf Rm-CR# 689
WebCast Link: https://bluejeans.com/s/jIoDx/
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
-
Sender Decomposition of Cache-Aided Communications and Distributed Computing
Thu, Oct 25, 2018 @ 01:00 PM - 02:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Petros Elia, Communication Systems Department, EURECOM, Sophia Antipolis, France
Talk Title: Sender Decomposition of Cache-Aided Communications and Distributed Computing
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: Recent results have shown that the data-redundancy that can exist in cache-aided communication networks as well as in (coded) distributed computing, can allow for substantial reductions in communication delays. These approaches though face various fundamental challenges that severely reduce the theoretically unbounded gains to much smaller gains. The work here shows a simple way without any additional data exchange between the communicating/computing nodes to decompose the problems of coded caching and coded distributed computing, into problems of smaller dimensionality with much better overall performance. Different manifestations of this "decomposition" phenomenon are explored, each revealing interesting boosts in performance and a direct amelioration of different bottlenecks like the "uneven category bottleneck", the "straggler bottleneck" and the "finite data-set bottleneck".
Biography: Petros Elia received the B.Sc. degree from the Illinois Institute of Technology, and the M.Sc. and Ph.D. degrees in electrical engineering from the University of Southern California in 2001 and 2006 respectively. He is a professor with the Department of Communication Systems at EURECOM, in Sophia Antipolis, France. His latest research deals with information-theoretic aspects of caching, as well with different problems in the area of complexity-constrained communications, coding theory, and surveillance networks. He is a Fulbright scholar, the co-recipient of the NEWCOM++ distinguished achievement award 2008-2011 for a sequence of publications on the topic of complexity in wireless communications, and the recipient of the ERC Consolidator Grant 2017-2022 on cache-aided wireless communications.
Host: Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
Internship/Job Search Open Forum
Thu, Oct 25, 2018 @ 04:00 PM - 05:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
Increase your career and internship knowledge of the internship/job search by attending this professional development Q&A moderated by Viterbi Career Connections staff or Viterbi employer partners.
For more information about Labs & Open Forums, please visit viterbicareers.usc.edu/workshops.Location: Ronald Tutor Hall of Engineering (RTH) - 211
Audiences: Everyone Is Invited
Contact: RTH 218 Viterbi Career Connections
-
MathWorks Day Seminar
Thu, Oct 25, 2018 @ 04:00 PM - 06:00 PM
USC Viterbi School of Engineering
Workshops & Infosessions
Join MathWorks engineers as they provide insight into the latest features of the MATLAB and Simulink product families.
Demystifying deep learning: A practical approach in MATLAB
-Manage extremely large sets of images
-Visualize networks and gain insight into the black box nature of deep networks
-Perform classification and pixel-level semantic segmentation on images
-Import training data sets from networks such as GoogLeNet and ResNet
-Import and use pre-trained models from TensorFlow and Caffe
-Speed up network training with parallel computing on a cluster
-Automate manual effort required to label ground truth
-Automatically convert a model to CUDA to run on GPUs
To register in advance: www.mathworks.com/USC2018
More Information: USC Poster.pdf
Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 106
Audiences: Everyone Is Invited
Contact: Michael Goay
