Colloquium

Compactness versus Robustness: Either or Both?

Deep networks were recently suggested to face the odds between accuracy (on clean natural data) and robustness (on adversarially perturbed data). Such a dilemma is shown to be rooted in the inherently higher sample complexity and/or model capacity, for learning a high-accuracy and robust classifier. In view of that, given a classification task, growing the model capacity appears to help draw a win-win between accuracy and robustness, yet at the expense of model size and latency.

AI for Public Health and Conservation: Learning and Planning in the Data-to-Deployment Pipeline

With the maturing of AI and multiagent systems research, we have a tremendous opportunity to direct these advances towards addressing complex societal problems. We focus on the problems of public health and wildlife conservation, and present research advances in multiagent systems to address one key cross-cutting challenge: how to effectively deploy our limited intervention resources in these problem domains. We present our deployments from around the world as well as lessons learned that we hope are of use to researchers who are interested in AI for Social Impact.

Thunder CTF: Learning Cloud Security on a Dime

Organizations have rapidly shifted infrastructure and applications over to public cloud computing services such as AWS, Google Cloud Platform, and Azure. Unfortunately, such services have security models that are substantially different and more complex than traditional enterprise security models. As a result, misconfiguration errors in cloud deployments have led to dozens of well-publicized breaches. This talk describes Thunder CTF, a scaffolded, scenario-based CTF for helping students learn about and practice cloud security skills.

Language Understanding in the Human Brain

How does the human brain use neural activity to create and represent meanings of the words, phrases, sentences and stories it reads? One way to study this question is to give people text to read while observing their brain activity. We have been doing such experiments with fMRI (1 mm spatial resolution) and MEG (1 msec time resolution) brain imaging, and developing novel machine learning approaches to analyze this data.

Directed Research Project Presentations

The first milestone in the CIS Ph.D. program is the Directed Research Project (DRP). Each student must complete this milestone within their first two years in the program. Typically, students devote the summer after their first year in the program exclusively to their research projects. In this colloquium, nine of our Department's Ph.D. students will present summaries on the progress on their DRP's over this past summer.

Faculty Research Topics

This week, we continue our introduction to faculty research topics. We encourage all faculty members and MS/PhD students to attend and hope these presentations would help students meet faculty members and get exposed to the full range of the research portfolio in our department. We feature the following speakers this week:

Faculty Research Topics

This week, we continue our introduction to faculty research topics. We encourage all faculty members and MS/PhD students to attend and hope these presentations would help students meet faculty members and get exposed to the full range of the research portfolio in our department. We feature the following speakers this week:

Collaborative Opportunities with CCDC ARL West

The Combat Capabilities Development Command (CCDC) Army Research Laboratory (ARL) has established a strong presence on the West Coast at its CCDC ARL West hub in Silicon Beach. Since the inception of ARL West in 2016, we have developed collaborations with universities across California and beyond. In order to develop stronger connections with the University of Oregon, ARL will be visiting several faculty to plan collaborative research. The delegation will include ARL West Regional Lead, Dr. Pete Khooshabeh, and other scientists and engineers, including, Mr.

Pages

Subscribe to RSS - Colloquium