Videos

Searching Images with Images: Characterization, Retrieval, and Ranking

3 weeks ago
High-throughput instruments such as those at national laboratories can produce terabytes of experimental data in seconds, and this rate keeps increasing. However, the available software tools to organize and retrieve images cover a small fraction of our needs. With significant improvements in image processing and availability of large data repositories, the development of methods to […]

Overcoming Fundamental Inefficiencies in the Representation of Data in Conventional Architectures

3 weeks ago
Society has become so dependent on computing power that any inefficiencies in the way that we process information can considerably impede productivity and quality of life. Three emerging trends pose challenges to the design of more efficient computer systems. First, energy constraints are becoming more strict amidst the rising interest in IoT and mobile computing. […]

Panel Discussion – Day 2

3 weeks ago
See more on this video at www.microsoft.com/en-us/research/video/panel-discussion-day-2/

Data Science for Social Good

3 weeks ago
See more on this video at www.microsoft.com/en-us/research/video/data-science-social-good/

Bayesian Deep Learning and Black Box Variational Inference

4 weeks ago
Scientists and scholars across many fields seek to answer questions in their respective disciplines using large data sets. One approach to answering such questions is to use probabilistic generative models. Generative models help scientists express domain knowledge, uncover hidden structure, and form predictions. In this talk, I present my work on making generative modeling more […]

Discriminative Learning of Social Dynamics

4 weeks ago
As a field concerned with prediction, machine learning is a natural candidate for approaching social-related prediction tasks. However, in contrast to many other domains were machine learning has been successfully applied, social phenomena remain notoriously hard to predict. In this talk I will argue that in addition to a large and rich data and powerful […]

Social Data Processing using Exchangeable Models

4 weeks ago
Social Data Processing using Exchangeable Models: Recommendation Systems, Crowd-sourcing, and Graphon Estimation Much of modern data is generated by humans and drives decisions made in a variety of settings, such as recommendations for online markets, analysis of social networks, or denoising crowdsourced labels. Due to the complexities of human behavior, the precise data model is […]

Improving Network Performance Through Endpoint Diagnosis

4 weeks ago
“Components of networks, and by extension the internet can fail. Users of the network (clients) do not have access to the various components of this distributed system. Therefore, it is important to provide them with tools so that they are able to handle such failures. This can be achieved in two ways. First, by helping […]

Building a Machine that Can Learn to Understand, Reason and Learn

4 weeks ago
My talk will first briefly review recent advances in memory augmented neural nets and then present my own contribution, Neural Semantic Encoders (NSE). With a special focus on NSE, I show that external memory in conjunction with attention mechanism are very useful in natural language understanding and reasoning. Particularly I will cover a set of […]

Antisocial Computing: Explaining and Predicting Negative Behavior Online

4 weeks ago
Antisocial behavior and misinformation are increasingly prevalent online. As users interact with one another on social platforms, negative interactions can cascade, resulting in complex changes in behavior that are difficult to predict. My research introduces computational methods for explaining the causes of such negative behavior and for predicting its spread in online communities. It complements […]

Safety Net and Springboard

4 weeks ago
A scalable programming language is one in which the same concepts can describe small as well as large parts. Towards this goal, the Scala programming language unifies concepts from object and module systems. In particular, objects can contain type members, which can be selected as types, called path-dependent types. Focusing on path-dependent types, we develop […]

Making the Fastest Routers Programmable

4 weeks ago
Historically, the evolution of network routers was driven primarily by performance. Recently, owing to the need for better control over network operations and the constant demand for new features, programmability of routers has become as important as performance. However, today’s fastest routers, which run at line rate, use fixed-function hardware, which cannot be modified after […]