Microsoft Research

Videos: 1924 Likes: 11,430 Views: 1,405,543

Videos by: Microsoft Research

Tales from the Crypt(ography) Lab with Dr. Kristin Lauter

6 days ago
From ancient hieroglyphics to secret decoder rings to World War II Enigma code-makers and code-breakers, cryptography has always held a particular fascination for us. But few of us have the skills – or can actually do the math – to unlock the mysteries of encrypted data. Fortunately, Dr. Kristin Lauter, distinguished mathematician, founder of the […]

Fireside Chat with Jon Kleinberg

1 week ago
Fireside Chat between Eric Horvitz and Jon Kleinberg. See more at www.microsoft.com/en-us/research/videos/ai-distinguished-lecture-series/

Fireside Chat with Tom Dietterich

1 week ago
Fireside Chat between Eric Horvitz and Tom Dietterich. See more at www.microsoft.com/en-us/research/videos/ai-distinguished-lecture-series/

Approximating General Norms by Euclidean Beyond the John’s Ellipsoid

1 week ago
John’s theorem proved in 1948 states that any centrally-symmetric convex body in R^d can be sandwiched by two ellipsoids up to a factor of sqrt{d}. In particular, it implies that any d-dimensional normed space embeds into a Euclidean space with distortion sqrt{d}, which is tight. During the talk, I will introduce an embedding found in […]

Anomaly Detection: Algorithms, Explanations, Applications

2 weeks ago
Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems. This talk will review recent work in our group on (a) benchmarking existing algorithms, (b) developing a theoretical understanding of their behavior, (c) explaining anomaly “alarms” to a data analyst, and (d) interactively re-ranking candidate anomalies in response to analyst feedback. Then the […]

Unsupervised Streaming Cyber-Analytics

2 weeks ago
The supervised learning approach to cyber-analytics has proven rather successful. However, there are challenges with this approach, including a frequent dearth of labelled data, the issue of temporal variation, and fundamentally, problems of data volume and velocity. In this talk, we describe simple unsupervised analytics intended to complement and enhance supervised methods. These approaches are […]

Neural Representations for Program Analysis and Synthesis

2 weeks ago
Representing a program as a numerical vector (i.e., neural representation) enables handling discrete programs using continuous optimization approaches, and thus opens up new opportunities to tackle many traditional challenging programming language problems. In this talk, I will introduce two directions of my research along this direction. First, I have been working on synthesizing programs from […]

DL Workspace: Running TensorFlow

3 weeks ago
The tutorial video is part of DL Workspace series, which describes an open source toolkit for turn-key AI Cluster setup and operation. This video explains the process to launch an interactive TensorFlow job in DL Workspace. See more at www.microsoft.com/en-us/research/group/cloud-computing-and-storage/

When Psychology Meets Technology with Dr. Daniel McDuff

3 weeks ago
Dr. McDuff talks about why we need computers to understand us, outlines the pros and cons of designing emotionally sentient agents, explains the technology behind CardioLens, a pair of augmented reality glasses that can take your heart rate by looking at your face, and addresses the challenges of maintaining trust and privacy when we’re surrounded […]

Monopoly Without a Monopolist: An Economic Analysis of Bitcoin

4 weeks ago
Owned by nobody and controlled by an almost immutable protocol, the Bitcoin payment system is a platform with two main constituencies: users and profit-seeking miners who maintain the system’s infrastructure. The paper seeks to understand the economics of the system: How does the system raise revenue to pay for its infrastructure? How are usage fees […]

Enabling Low-power Computation, Sensing, and Communication on Internet-of-Things

4 weeks ago
In recent years, we have seen a massive number of IoT devices shipped to the market. The vision is that we are going to embrace a world where IoT devices are ubiquitously deployed. However, this vision is limited by problems arise in three areas — wireless connectivity, energy-efficient computing and IoT data analytics. The wireless […]

Generalization Error Bounds for Extreme Multi-class Classification

4 weeks ago
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document tagging in NLP, face recognition to learning universal feature representations in computer vision, gene function prediction in bioinformatics, etc. Extreme […]