Videos

Oral Session: End-To-End Memory Networks

Oral Session: End-To-End Memory Networks

2 years ago
We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network (Weston et al., 2015) but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. […]
Coalescence in Branching Trees and Branching Random Walks

Coalescence in Branching Trees and Branching Random Walks

2 years ago
Consider a branching tree with one root at the origin. Assuming that at the n -th level there are at least two vertices. Pick two of them by simple random sampling without replacement. Now trace their lines back till they meet. Call that level X n . In this talk we discuss the behavior of […]
Oral Session: Deep Visual Analogy-Making

Oral Session: Deep Visual Analogy-Making

2 years ago
In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding. Recently, deep convolutional networks have yielded breakthroughs in producing image labels, annotations and captions, but have only just begun to be used for producing high-quality image outputs. In this paper we develop a […]
Panel Discussion: The State of Audio Education in the Pacific Northwest

Panel Discussion: The State of Audio Education in the Pacific Northwest

2 years ago
Decades ago, when the audio industry was in its infancy, there was no way to get formal education in Audio Engineering. You hung out at a studio, maybe and maybe you got a job sweeping floors, running coffee, etc. which maybe led to helping with setups, 2nd engineering, and some day: your first session. Or […]
Panel: Progress in AI: Myths, Realities, and Aspirations

Panel: Progress in AI: Myths, Realities, and Aspirations

2 years ago
Moderated by Eric Horvitz, Managing Director, Microsoft Research Panelists: Fei-Fei Li, Associate Professor, Stanford University Michael Littman, Professor of Computer Science, Brown University Josh Tenenbaum, Professor, Massachusetts Institute of Technology Oren Etzioni, Chief Executive Officer, Allen Institute for Artificial Intelligence Christopher Bishop, Distinguished Scientist, Microsoft Research
Juggling the Effects of Latency: Motion Prediction Approaches to Reducing Latency in Dynamic Project

Juggling the Effects of Latency: Motion Prediction Approaches to Reducing Latency in Dynamic Project

2 years ago
In this video, we focus our predictive approaches on real-world objects under fast motion and on-body projection, improving projection accuracy on fast moving targets. Alongside this we explore automatic latency measurement techniques, allowing our system to determine and account for its own latency. research.microsoft.com/
Panel 3: Measuring Content: Evaluation, Metrics and Measuring Impact

Panel 3: Measuring Content: Evaluation, Metrics and Measuring Impact

2 years ago
Chair Gregg Gordon, President, Social Science Research Network, will lead a panel discussion on evaluation and impact “beyond citations” for articles, researchers, institutions.
How to Write a Great Research Paper

How to Write a Great Research Paper

2 years ago
Writing papers and giving talks are key skills for any researcher, but they aren’t easy. In this pair of presentations, It’ll describe simple guidelines that I follow for writing papers and giving talks, which I think may be useful to you too. I don’t have all the answers — far from it — and I […]
DNA Join circuit

DNA Join circuit

2 years ago
A Join circuit implemented in DNA.
Bing Code Search Add-in for Visual Studio 2013

Bing Code Search Add-in for Visual Studio 2013

2 years ago
The Bing Code Search add-in allows you to search and reuse code snippets directly inside Visual Studio.
Tutorial: Introduction to Reinforcement Learning with Function Approximation

Tutorial: Introduction to Reinforcement Learning with Function Approximation

2 years ago
Reinforcement learning is a body of theory and techniques for optimal sequential decision making developed in the last thirty years primarily within the machine learning and operations research communities, and which has separately become important in psychology and neuroscience. This tutorial will develop an intuitive understanding of the underlying formal problem (Markov decision processes) and […]
Tutorial: Deep Learning

Tutorial: Deep Learning

2 years ago
Deep Learning allows computational models composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection, and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large datasets by using […]