Upcoming Events

Designing Matching Algorithms and Collaborative Project Experiences in Computer Science

Duke Computer Science Colloquium
Speaker Name
Brandon Fain
Location
LSRC D106
Date and Time
-
In the first part of the talk, we will consider the design of two-sided matching algorithms for problems like residency matching and school choice. In the second half of the talk, we will step back and consider how the approach of the first half reflects a larger goal of engaging students in the process of becoming computer scientists through active and collaborative learning.

Engineering Responsible AI

Duke Electrical Computer Engineering Colloquium
Speaker Name
Harry Shum
Location
Penn Pavilion
Date and Time
-
Recent achievements and advancements in AI have outpaced what anyone would have thought imaginable even five to ten years ago. In this talk, I will share some examples of what we have been practicing in Microsoft AI and Research from doing research in explainable and interpretable AI, to creating tools for bias error analysis in machine learning, to debiasing word embedding learnt from the web.

Foundations of Intelligent Systems with (Deep) Function Approximators

Duke Computer Science Colloquium
Speaker Name
Simon Du
Location
LSRC D106
Date and Time
-
In this talk, I will discuss my work on understanding, designing, and applying function approximators. First, I will focus on understanding deep neural networks. In the second part of the talk, I will focus on applying function approximators to decision-making, aka reinforcement learning, problems.

How to Use and Teach Runtime Analysis

Duke Computer Science Colloquium
Speaker Name
Miranda Parker
Location
LSRC D106
Date and Time
-
In this talk, I will first introduce what big-O analysis is and its importance in computer science. Then I will discuss sorting algorithms, particularly insertion and merge sorts. I will also discuss prior research on how students learn big-O analysis, discussing the difficulties that arise at the intersection of mathematics and computer science and how that influenced the approach I used to teach runtime analysis.

Data-Powered Patient-Centered Care

Miscellaneous Talk
Speaker Name
Noemie Elhadad
Location
Bryan Research Room 103
Date and Time
-

Despite the pervasive deployment of electronic health record systems, their promise to streamline entering and retrieving clinical data, and the recent advances in artificial intelligence in healthcare, getting meaningful and actionable information at the point of care is still a formidable challenge for clinicians. In this talk, I will present our approach to designing, building, and deploying tools to support clinicians in their decision-making workflow, as well as facilitating the patient-provider partnership in shared-decision making. 

Where Natural Language Processing Meets Societal Needs

Triangle Computer Science Distinguished Lecturer Series
Speaker Name
Kathleen McKeown
Location
LSRC D106
Date and Time
-

The large amount of language available online today makes it possible to think about how to learn from this language to help address needs faced by society. In this talk, I will describe research in our group on summarization and social media analysis that addresses several different challenges. We have developed approaches that can be used to help people live and work in today’s global world, approaches to help determine where problems lie following a disaster, and approaches to identify when the social media posts of gang-involved youth in Chicago express either aggression or loss.

Introduction to Methods / Look for the Helpers: Creating and Maintaining a Culture of Allyship and Advocacy in Computing

Duke Computer Science Colloquium
Speaker Name
Nicki Washington
Location
LSRC D106
Date and Time
-
In the first part of this talk, I will provide a sample lesson on methods using strategies to help learners understand their general purpose and how they are implemented in Java. The second part of my talk discusses how my work both in and out of the classroom helps to foster a culture where allyship and advocacy is not only celebrated, encouraged, and nurtured, but also expected.

Neural Control of Movement: How We Move Fast, Why We Fail, and How We Can Design Interventions

Miscellaneous Talk
Speaker Name
Shreya Saxena
Location
Gross Hall 330
Date and Time
-
Animals (including humans) have a remarkable ability to effortlessly perform complex and fast movements. In the first part of my talk, I will focus on performance limitations of sensorimotor control. In the second part of my talk, I will focus on how the primate brain flexibly generates movements at different speeds.

Designing for the Last Mile of Machine Learning

Miscellaneous Talk
Speaker Name
Berk Ustun
Location
Gross Hall 330
Date and Time
-

Machine learning is now a general-purpose technology. In many domains, we can build models to support important decisions or automate routine tasks. Yet we may not reap their benefits due to disuse, or inflict harm due to misuse. In this talk, I will present methodological advances that address these "last mile" challenges in healthcare applications. First, I will describe a method to learn simple risk scores that are readily adopted for medical decision support, and discuss applications to adult ADHD diagnosis and ICU seizure prediction.

Digital Forensics: From Photoshop to Deep Fakes

Triangle Computer Science Distinguished Lecturer Series
Speaker Name
Hany Farid
Location
LSRC D106
Date and Time
-

The past few years have seen a startling and troubling rise in the fake-news phenomena in which everyone from individuals to state-sponsored entities can produce and distribute mis-information. The implications of fake news range from a mis-informed public to an existential threat to democracy, and horrific violence. At the same time, recent and rapid advances in machine learning are making it easier than ever to create sophisticated and compelling fake images and videos, making the fake-news phenomena even more powerful and dangerous.

DNA Information Systems and Cancer Classification

Miscellaneous Talk
Speaker Name
Siddharth Jain
Location
Gross Hall 330
Date and Time
-
By calculating mutation profiles from the blood derived genomic data of more than 5000 cancer patients on The Cancer Genome Atlas (TCGA), we demonstrate using machine learning that these profiles can distinguish between patients with various types of cancer. Our results show that healthy cells still contain a cancer-specific signal, which opens the possibility of cancer prediction from a healthy genome.

Building Distributed Systems Using Programmable Networks

Duke Computer Science Colloquium
Speaker Name
Ming Liu
Location
LSRC D106
Date and Time
-
In this talk, I will present two frameworks for building PNF-enabled distributed systems: (1) IncBricks, an in-network caching fabric built with network accelerators and programmable switches; (2) iPipe, an actor-based framework for offloading distributed applications onto SmartNICs. I will show how to make efficient use of in-network heterogeneous computing resources by applying approximation techniques, co-designing with end-host software layers, employing new programming abstractions, and designing efficient control-/data-planes.

Putting Ethical AI to the Vote

Triangle Computer Science Distinguished Lecturer Series
Speaker Name
Ariel Procaccia
Location
LSRC D106
Date and Time
-

I will present the 'virtual democracy' framework for the design of ethical AI. In a nutshell, the framework consists of three steps: first, collect preferences from voters on example dilemmas; second, learn models of their preferences, which generalize to any (previously unseen) dilemma; and third, at runtime, predict the voters' preferences on the current dilemma, and aggregate these virtual 'votes' using a voting rule to reach a decision.