Once every week while school is in session, EECS invites a distinguished researcher or practitioner in a computer science or electrical and computer engineering-related field to present their ideas and/or work. Talks are generally targeted to electrical engineering and computer science graduate students. This colloquium series is free and open to everyone.

Upcoming Colloquia

Headwind and Drag - Forces That Impede The Grad Student

Monday, February 17, 2020 - 4:00pm to 4:50pm
Linus Pauling Science Center 125

Speaker Information

Jed Irvine
Senior Faculty Research Assistant
School of EECS
Oregon State University

Abstract

 A grad student knows how challenging the academic aspects of their work can be.  There also can be challenges in two other areas that can slow progress: issues around the collaboration dynamics with the adviser and student work habit issues.  These challenges are not always visible - these I refer to as "headwind" - an invisible force that slows you down.  Some challenges are visible, but the student may be unable to realize that the problem may have a solution (more headwind), or perhaps they see a path towards a solution, but are unable to work towards it.  I call the latter case "drag" - thoughts or feelings that arise in the student that work to slow them down. In this talk, I will give examples of headwind and drag and offer techniques to overcome them.

 

Speaker Bio

Jed Irvine is a Senior Faculty Research Assistant in EECS.   He began his career with twenty years of work in government and the private sector.  He joined OSU in 2004 as a software developer, and has supported numerous research projects involving machine learning.  In 2018, he began coaching grad students on addressing obstacles to progress that are unrelated to their focus of study.

Robust Methods for Topology Estimation in Unsupervised Learning

Monday, February 24, 2020 - 4:00pm to 4:50pm
Linus Pauling Science Center 125

Speaker Information

Shay Deutsch
Assistant Adjunct Professor
Mathematics Department
University of California, Los Angeles

Abstract

Learning graph connectivity has broad-ranging applications from 3D reconstruction to unsupervised learning. In this talk I will introduce a new method to learn the graph structure underlying noisy point set observations assumed to lie near a complex manifold. Rather than assuming regularity of the manifold itself, as customary, we assume regularity of the geodesic flow through the boundary of arbitrary regions on the graph. The idea is to exploit this more flexible notion of regularity, captured by the discrete equivalent of the isoperimetric inequality for closed manifolds, to infer the graph structure.

In a broader perspective, when studying the topology of the graph networks, we would like to learn new representations that capture not only local connectivity, i.e., nodes that belong to the same local structure, but also similarity which is based on their structural role in the graph. I will discuss a new approach and vision towards learning a good trade-off between these local and structural types of similarities that includes diverse possible applications including point clouds, biological networks and social networks.

Speaker Bio

Shay Deutsch received a B.Sc. in Mathematics from the Technion—Israel Institute of Technology in 2007, an M.Sc. in Applied Mathematics from Tel Aviv University in 2010, and a Ph.D. in Computer Science from the University of Southern California (USC) in 2016. He is currently an Assistant Adjunct Professor in the Mathematics Department at the University of California, Los Angeles (UCLA). His research work is in the union of transfer learning, graph signal processing and graph networks, where his research is dedicated to developing robust methods for unsupervised learning. His most recent research efforts focus on developing cohesive relations between embedding topology and graph networks using uncertainty principles on graphs.

Past Colloquia

Rene Just
Tuesday, March 10, 2015 - 10:00am to 11:00am
Matthew Johnston
Monday, March 9, 2015 - 4:00pm to 4:50pm
Michael S. Ryoo
Friday, March 6, 2015 - 9:00am to 10:00am
Hamed Pirsiavash
Thursday, March 5, 2015 - 10:00am to 11:00am
Michael Thorburn
Friday, February 27, 2015 - 2:00pm to 3:00pm
Arijit Khan
Thursday, February 26, 2015 - 10:00am to 11:00am
Sandeep Kaur Kuttal
Monday, February 23, 2015 - 4:00pm to 4:50pm
Myounggyu Won
Wednesday, February 18, 2015 - 8:45am to 9:45am
Philip Asare
Monday, February 16, 2015 - 8:45am to 9:45am
Masood Parvania
Friday, February 13, 2015 - 8:45am to 9:45am

Pages