Microsoft Research

Videos: 1731 Likes: 9,949 Views: 1,360,318

Videos by: Microsoft Research

Artificial Intelligence to Ease Parents’ Pain in Summer Camp Planning

1 day ago
Today, one can Lyft a ride and AirBnb home away from home all in minutes. However, when comes to planning for our children’s enrichment activities, it takes us poor parents hours and days. Now 6crickets.com is going to change all that. 6crickets offers one easy stop for parents to discover, schedule, book and share children’s […]

Machine Learning from Verbal Instruction

3 days ago
Unlike traditional machine learning methods, humans often learn from natural language instruction. As users become increasingly accustomed to interacting with computer devices using speech, their interest in instructing these devices in natural language is likely to grow. We present our Learning by Instruction Agent (LIA), an intelligent personal agent that users can teach to perform […]

DISCO Nets: DIssimilarity COefficient Networks

6 days ago
The DISCO Nets is a new type of probabilistic model for estimating the conditional distribution over a complex structured output given an input. DISCO Nets allows efficient sampling from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated […]

Grammar Variational Autoencoder

6 days ago
Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often produce outputs that are not valid. We make the key observation that frequently, discrete […]

Bayesian optimisation in many dimensions with bespoke models

6 days ago
Bayesian optimisation (BO) is an optimisation method which incrementally builds a statistical model of the objective function to refine its search. Unfortunately, due to the curse of dimensionality, BO can fail to converge in problems with many dimensions. In this talk, I will show how better priors for BO can result in orders of magnitude […]

Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

6 days ago
We present an algorithm for policy search in stochastic dynamical systems using model-based reinforcement learning. The system dynamics are described with Bayesian neural networks (BNNs) that include stochastic input variables. These input variables allow us to capture complex statistical patterns in the transition dynamics (e.g. multi-modality and heteroskedasticity), which are usually missed by alternative modeling […]

Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning

1 week ago
Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning. Estimating latent quantities in a generative model provides a principled framework, and has been successfully used in the linear case, e.g. with independent component analysis (ICA) and sparse coding. However, extending ICA to the nonlinear case has proven […]

Predicting 3D Volume and Depth from a Single View

1 week ago
A single glimpse is hardly enough to triangulate the 3D shapes of a scene. However, training examples are readily available, so statistical models can be trained to map appearance to shape. The details matter, because 3D shapes have different representations and can have many degrees of freedom, and training data is rarely as clean as […]

Microsoft Security Risk Detection Helps Digital Transaction Management company DocuSign

2 weeks ago
Taking paper-driven processes online isn’t easy – but keeping it secure is a whole other matter. To help, global eSignature and Digital Transaction Management (DTM) leader DocuSign recently used Microsoft Security Risk Detection to provide additional assurance, ensuring its code is always ready to match today’s security threats. See more on this video at www.microsoft.com/en-us/research/video/microsoft-security-risk-detection-helps-digital-transaction-management-company-docusign/

Automating and Testing Program Transformations using Program Synthesis

2 weeks ago
Automatic program transformation tools can be valuable for programmers to help them with refactoring tasks, and for Computer Science students in the form of tutoring systems that suggest repairs to programming assignments. However, manually implementing and testing catalogs of transformations is complex and time-consuming. In this talk, I will present two program synthesis-based techniques for […]

Seeing Experience from Many Angles: Educational Game Design as a Data-Informed Craft

2 weeks ago
Increasingly, educational games have become an established part of the instructional landscape, however designing a compelling and effective instructional game remains a challenge. One of the reasons for this challenge is that game players are afforded some agency to craft their own experiences, making it difficult to anticipate the kinds of experiences they might have. […]

Streaming Lower Bounds for Approximating MAX-CUT

2 weeks ago
We consider the problem of estimating the value of MAX-CUT in a graph in the streaming model of computation. We show that there exists a constant $e_* > 0$ such that any randomized streaming algorithm that computes a $(1+e_*)$-approximation to MAX-CUT requires $Omega(n)$ space on an $n$ vertex graph. By contrast, there are algorithms that […]