Videos

Recent Advances in Deep Learning at Microsoft: A Selected Overview

Recent Advances in Deep Learning at Microsoft: A Selected Overview

2 years ago
Since 2009, Microsoft has engaged with academic pioneers of deep learning and has created industry-scale successes in speech recognition as well as in speech translation, object recognition, automatic image captioning, natural language, multimodal processing, semantic modeling, web search, contextual entity search, ad selection, and big data analytics. Much of these successes are attributed to the […]
Probability and Prejudice: Bridging the Gap Between Machine Learning and Programming Languages

Probability and Prejudice: Bridging the Gap Between Machine Learning and Programming Languages

2 years ago
Probabilistic programming languages are often thought of as a point of intersection between machine learning and programming languages. While this is true in some respects, they mostly occupy a gap between the two research areas. Technically, correctly running all probabilistic programs requires different algorithms, formalisms and theory than than are commonly used in either area. […]
Madoko: a scholarly markdown

Madoko: a scholarly markdown

2 years ago
During this talk I will be giving a demo of Madoko: a scholarly markdown processor that enables light-weight creation of high-quality scholarly and industrial documents with a focus on simplicity and plain text readability. In particular, Madoko is quite more pleasant to write than LaTeX, and can generate both high-quality HTML and PDF (through LaTeX). […]
Practical Learning Algorithms for Structured Prediction

Practical Learning Algorithms for Structured Prediction

2 years ago
Machine learning techniques have been widely applied in many areas. In many cases, high accuracy requires training on large amount of data, adding more expressive features and/or exploring complex input and output structures, often resulting in scalability problems. Nevertheless, we observed that by carefully selecting and caching samples, structures, or latent items, we can reduce […]
Experiences with Scaling Blockchain-based Data Stores

Experiences with Scaling Blockchain-based Data Stores

2 years ago
In the past years cryptocurrency blockchains (like Bitcoin and Namecoin) have seen significant adoption with the promise of using such blockchains as general-purpose databases and/or key-value stores. Cryptocurrency blockchains provide a zero-trust infrastructure, where users can securely store and retrieve information while providing security guarantees that only the owner of a particular private-key can write/modify […]
DataHub and E-Store

DataHub and E-Store

2 years ago
DataHub: A Hosted Platform for Organizing, Managing, Sharing, Collaborating, and Processing Data In this talk, I will describe DataHub – a hosted data collaboration platform we are building at MIT. DataHub is a unified data management and collaboration platform. The DataHub platform is (a) a flexible data-store (files, relational databases, extendible to other data-storage backends) […]
Near Future Laboratory

Near Future Laboratory

2 years ago
A talk from the Social Computing Symposium.
Context-aware programming languages

Context-aware programming languages

2 years ago
Modern computer programs do not run in the void. They run in rich environments that provide important data sources, services and other functionality that is required by the programs. For example, mobile applications access GPS locations, call server-side code over the network, access data from public REST-based services and so on. Yet, programming languages often […]
The Forza Motorsport 5 Original Soundtrack, An Insider’s View

The Forza Motorsport 5 Original Soundtrack, An Insider’s View

2 years ago
Video Title: The Forza Motorsport 5 Original Soundtrack, An Insider’s View Video File Created Date: Thursday, June 9, 2016 (Video may or may not have been captured on this date, it shows the date the video was last converted.)The session “The Forza Motorsport 5 Original Soundtrack, An Insider’s View” is a detailed look at how […]
Optimal Design for Social Learning

Optimal Design for Social Learning

2 years ago
We study the design of a recommender system for organizing social learning on a product. The optimal design trades off fully transparent social learning to improve incentives for early experimentation, by selectively over-recommending a product in the early phase of the product release. Under the optimal scheme, experimentation occurs faster than under full transparency but […]
Introduction to Machine Learning in Python with Scikit-Learn

Introduction to Machine Learning in Python with Scikit-Learn

2 years ago
This talk will introduce scikit-learn, an Open Source project for Machine Learning in Python and review some new features from the recent 0.15 release: faster randomized ensemble of decision trees and optimization for the memory usage when working on multiple cores. Finally we will demo the typical usage of scikit-learn for interactive predictive analytics in […]
Local Deep Kernel Learning for Efficient Non-linear SVM Prediction

Local Deep Kernel Learning for Efficient Non-linear SVM Prediction

2 years ago
The time taken by an algorithm to make predictions is of critical importance as machine learning transitions to becoming a service available on the cloud. Algorithms that are efficient at prediction can service more calls and utilize fewer cloud resources and thereby generate more revenue. They can also be used in real time applications where […]