Past events

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Thursday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Johannes Royset (Naval Postgraduate School), will be giving a talk titled "Diametrical Risk Minimization: Theory and Computations."

Abstract

The theoretical and empirical performance of Empirical Risk Minimization (ERM) often suffers when loss functions are poorly behaved with large Lipschitz moduli and spurious sharp minimizers. We propose and analyze a counterpart to ERM called Diametrical Risk Minimization (DRM), which accounts for worst-case empirical risks within neighborhoods in parameter space. DRM has generalization bounds that are independent of Lipschitz moduli for convex as well as nonconvex problems and it can be implemented using a practical algorithm based on stochastic gradient descent. Numerical results illustrate the ability of DRM to find quality solutions with low generalization error in sharp empirical risk landscapes from benchmark neural network classification problems with corrupted labels.

Biography

Dr. Johannes O. Royset is Professor of Operations Research at the Naval Postgraduate School. Dr. Royset's research focuses on formulating and solving stochastic and deterministic optimization problems arising in data analytics, sensor management, and reliability engineering. He was awarded a National Research Council postdoctoral fellowship in 2003, a Young Investigator Award from the Air Force Office of Scientific Research in 2007, and the Barchi Prize as well as the MOR Journal Award from the Military Operations Research Society in 2009. He received the Carl E. and Jessie W. Menneken Faculty Award for Excellence in Scientific Research in 2010 and the Goodeve Medal from the Operational Research Society in 2019. Dr. Royset was a plenary speaker at the International Conference on Stochastic Programming in 2016 and at the SIAM Conference on Uncertainty Quantification in 2018. He has a Doctor of Philosophy degree from the University of California at Berkeley (2002). Dr. Royset has been an associate or guest editor of SIAM Journal on Optimization, Operations Research, Mathematical Programming, Journal of Optimization Theory and Applications, Naval Research Logistics, Journal of Convex Analysis, Set-Valued and Variational Analysis, and Computational Optimization and Applications. He is the author of about 100 papers and two books.

Have all your questions about the Master of Science in Software Engineering (MSSE) program answered by attending this online information session.

RSVP now to reserve your spot.

Attendees will be sent a link prior to the event.
 

Registration Required

The Minnesota Robotics Institute (MnRI) is an outcome of the University of Minnesota’s Discovery, Research, and InnoVation Economy (MnDRIVE) initiative that brings together interdisciplinary researchers to solve grand challenges and increase Minnesota’s position as a worldwide leader in robotics research and education.

Join MnRI Director Nikos Papanikoloupoulous, CS&E faculty members Hyun Soo Park and Maria Gini, and Graduate Program Advisor Travis Henderson to learn about the Institute’s mission, hear about the new M.S. in Robotics program, and take a virtual tour inside the MnRI’s world-class facilities. The presentation will also highlight recent research projects, including 3D reconstruction of dynamic human geometry, and how to allocate tasks depending on the number of robots available.

Register for the Zoom Webinar!

Spring semester registration begins for students admitted to degree or certificate programs on Tuesday, November 9.

View the full academic schedule on One Stop.
 

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's talk is a part of the Cray Distinguished Speaker Series. This series was established in 1981 by an endowment from Cray Research and brings distinguished visitors to the Department of Computer Science & Engineering every year.

Our speaker, Doug Bowman (Virginia Tech), will be giving a talk titled "User Experience Considerations for Everyday Augmented Reality."

Abstract

Future AR glasses will be much like today’s smartphones, as our everyday information access and productivity devices. Technical challenges in optics, power, and tracking remain, but are solvable. However, technical achievements alone are insufficient to ensure that everyday AR systems will be productive, usable, useful, and satisfying. We must also design effective methods for interacting with and managing AR content, and we must understand the effects of always-on AR, on both individuals and communities. In this talk, I will present a vision of future everyday AR use cases, and discuss recent user experience (UX) research aimed at enabling this vision. I will discuss UX design recommendations for making information access through AR more convenient and usable than today’s smartphones and smartwatches, while at the same time not distracting users from what’s going on in the real world around them.

Biography

Doug A. Bowman is the Frank J. Maher Professor of Computer Science and Director of the Center for Human-Computer Interaction at Virginia Tech. He is the principal investigator of the 3D Interaction Group, focusing on the topics of three-dimensional user interface design and the benefits of immersion in virtual environments. Dr. Bowman is one of the co-authors of 3D User Interfaces: Theory and Practice. He has served in many roles for the IEEE Virtual Reality Conference, including program chair, general chair, and steering committee chair. He also co-founded the IEEE Symposium on 3D User Interfaces (now part of IEEE VR). He received a CAREER award from the National Science Foundation for his work on 3D Interaction, and has been named an ACM Distinguished Scientist. He received the Technical Achievement award from the IEEE Visualization and Graphics Technical Committee in 2014. His undergraduate degree in mathematics and computer science is from Emory University, and he received his M.S. and Ph.D. in computer science from the Georgia Institute of Technology.

This week's speaker, Andrew Hansen, will be giving a talk titled "Development and Translation of Products for Veterans – Made by MADE."

Abstract

This presentation will provide an overview of the Minneapolis Adaptive Design & Engineering (MADE) Program’s history and development of products for Veterans. The MADE Program specializes in the development of rehabilitation technologies such as lower-limb prostheses, wheelchairs, exercise equipment, and skin screening systems. We utilize a stage-gate model for product development and work on projects that aim to improve the participation of Veterans in important life activities regardless of their physical abilities. MADE is also a site for the Technology Transfer Assistance Program, which serves to prototype clinician-driven ideas throughout the country.

Biography

Hansen received a bachelor’s degree in biomedical engineering from the University of Iowa in 1995, preceding his master’s and Ph.D. degrees in biomedical engineering from Northwestern University in 1998 and 2002. In 2010, Dr. Hansen and Dr. Gary Goldish founded the MADE Program, which has grown to over 25 multidisciplinary personnel in 2021. Dr. Hansen directs the MADE Program at the Minneapolis VA as a Research Biomedical Engineer, and is also a Professor of Rehabilitation Science and Biomedical Engineering at the University of Minnesota.

The Department of Computer Science & Engineering will be hosting an in-person event for prospective students on Friday, November 5 from 2-3 p.m.

At this on-campus event, you will have the chance to hear from, and connect with, current students and faculty in our Computer Science and Data Science graduate programs.

For more details on the event and to RSVP, please visit our sign up form. Space may be limited.

We hope to see you there!

For those who will not be able to attend in-person, this session will be recorded and available to view at a later date. We also encourage you to sign up for one of our virtual information sessions to learn more about our graduate programs and application details.

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Thursday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Junzhou Huang (University of Texas at Arlington), will be giving a talk titled "Deep Graph Learning for Drug Property Prediction."

Abstract

Graphs are powerful mathematical structures to describe relations or interactions among objects in different fields, such as biology, social science, economics and so on. Recent technological innovations are enabling scientists to capture enormous graph-structured data at increasing speed and scale. Thus, a compelling need exists to develop novel learning tools to foster and fuel the next generation of scientific discovery in graph data related research. However, the major computational challenges are due to the unprecedented scale and complexity of complex graph data analytics. There is a critical need for large-scale learning strategies with theoretical guarantees to bridge the gap and facilitate knowledge discovery from complex graph data. This talk will introduce our recent work on developing novel deep graph learning methods to efficiently and effectively process atom graph data for predicting the chemical or biological properties of drug molecules.

Biography

Dr. Junzhou Huang is a professor in the department of computer science and engineering at the University of Texas, Arlington. He received the Ph.D. degree in Computer Science at Rutgers, The State University of New Jersey. His major research interests include machine learning, computer vision, computational pathology, computational drug discovery and clinical science. He was selected as one of the 10 emerging leaders in multimedia and signal processing by the IBM T.J. Watson Research Center in 2010. His work won the MICCAI Young Scientist Award 2010, the FIMH Best Paper Award 2011, the STMI Best Paper Award 2012, the MICCAI Best Student Paper Award 2015, the 1st place of the Tool Presence Detection Challenge at M2CAI 2016, the 6th place in the 3D Structure Prediction Challenge and the 1st place in the Contact and Distance Prediction Challenge at CASP14, 2020 and the Google TensorFlow Model Garden Award 2021. He received the NSF CAREER Award 2016.

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Alice Oh (KAIST), will be giving a talk titled "Mitigating Language-Dependent Ethnic Bias in BERT."

Abstract

BERT and other large-scale language models (LMs) contain gender and racial bias. They also exhibit other dimensions of social bias, most of which have not been studied in depth, and some of which vary depending on the language. In this talk, I present a study of ethnic bias and how it varies across languages by analyzing and mitigating ethnic bias in monolingual BERT for English, German, Spanish, Korean, Turkish, and Chinese. To observe and quantify ethnic bias, we develop a novel metric called Categorical Bias score. Then we propose two methods for mitigation; first using a multilingual model, and second using contextual word alignment of two monolingual models. We compare our proposed methods with monolingual BERT and show that these methods effectively alleviate the ethnic bias. Which of the two methods works better depends on the amount of NLP resources available for that language. We additionally experiment with Arabic and Greek to verify that our proposed methods work for a wider variety of languages.

Biography

Alice Oh is a Professor in the School of Computing at KAIST. She received her PhD in 2008 from MIT and joined KAIST in the same year. Her major research area is at the intersection of machine learning and computational social science. Within machine learning, she studies various models designed for analyzing written text including social media posts, news articles, and personal conversations. She also looks at non-textual data such as social network friendship and logs from online games for which she interacts closely with social scientists for an interdisciplinary approach to computational social science. She has served as Tutorial Chair for NeurIPS 2019, Diversity & Inclusion Chair for ICLR 2019, and Program Chair for ICLR 2021. She is serving as Program Chair for NeurIPS 2022 and General Chair for ACM FAccT 2022.

This week's speaker, Junaed Sattar, will be giving a talk titled "From ideas to implementations: challenges of robot deployment in the field."

Abstract

Field robotics is all about deploying robotic systems in natural, and often hostile, conditions to evaluate their performance in realistic settings. In the case of our Interactive Robotics and Vision Lab, it involves deploying autonomous underwater robots in open-water environments -- open seas and lakes. This talk will try to give some insights into the journey from the drawing board to the dive board, with a focus on highlighting the process of conceiving algorithms for underwater robotics, specifically for visual perception, learning, human-robot interaction, and navigation, to field testing the entire system.

Biography

Junaed Sattar is an assistant professor at the Department of Computer Science and Engineering at the University of Minnesota and a MnDrive (Minnesota Discovery, Research, and Innovation Economy) faculty, and a member of the Minnesota Robotics Institute. He is the founding director of the Interactive Robotics and Vision Lab, where he and his students investigate problems in field robotics, robot vision, human-robot communication, assisted driving, and applied (deep) machine learning, and develop rugged robotic systems. His graduate degrees are from McGill University in Canada, and he has a BS in Engineering degree from the Bangladesh University of Engineering and Technology. Before coming to the UoM, he worked as a post-doctoral fellow at the University of British Columbia where his research focused on human-robot dialog and assistive wheelchair robots, and at Clarkson University in New York as an Assistant Professor. Find him at junaedsattar.info, and the IRV Lab at irvlab.cs.umn.edu, @irvlab on Twitter, and their YouTube page at https://www.youtube.com/channel/UCbzteddfNPrARE7i1C82NdQ.