Videos

Approximate Majority algorithm

Approximate Majority algorithm

2 years ago
A distributed algorithm for computing the majority between two populations.
Symposium: Brains, Minds and Machines – Joshua Tenenbaum

Symposium: Brains, Minds and Machines – Joshua Tenenbaum

2 years ago
Building Machines That Learn like Humans What is the essence of human intelligence — what makes any human child smarter than any artificial intelligence system that has ever been built? Recent advances in machine learning and computer vision are extremely impressive as engineering accomplishments, but are far from approaching learning and perception the way humans […]
DNA Strand Displacement

DNA Strand Displacement

2 years ago
A 3D animation of DNA strand displacement.
Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming

Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming

2 years ago
Gaming on phones, tablets and laptops is very popular. Cloud gaming — where remote servers perform game execution and rendering on behalf of thin clients that simply send input and display output frames — promises any device the ability to play any game any time. Unfortunately, the reality is that wide-area network latencies are often […]
Provable Algorithms for Learning Neural Networks

Provable Algorithms for Learning Neural Networks

2 years ago
We study the learning of fully connected neural networks for binary classification. For the networks of interest, we assume that the L1-norm of the incoming weights of any neuron is bounded by a constant. We further assume that there exists a neural network which separates the positive and negative samples by a constant margin. Under […]
Modern Deep Learning through Bayesian Eyes

Modern Deep Learning through Bayesian Eyes

2 years ago
Bayesian models are rooted in Bayesian statistics, and easily benefit from the vast literature in the field. In contrast, deep learning lacks a solid mathematical grounding. Instead, empirical developments in deep learning are often justified by metaphors, evading the unexplained principles at play. These two fields are perceived as fairly antipodal to each other in […]
Towards Understandable Neural Networks for High Level AI Tasks; Part 2

Towards Understandable Neural Networks for High Level AI Tasks; Part 2

2 years ago
Towards Understandable Neural Networks for High Level AI Tasks; Part 2.
Towards Understandable Neural Networks for High Level AI Tasks – Part 4

Towards Understandable Neural Networks for High Level AI Tasks – Part 4

2 years ago
Overview of talk series: Current AI software relies increasingly on neural networks (NNs). The universal data structure of NNs is the numerical vector of activity levels of model neurons, typically with activity distributed widely over many neurons. Can NNs in principle achieve human-like performance in higher cognitive domains – such as inference, planning, grammar – […]
What are the prospects for automatic theorem proving?

What are the prospects for automatic theorem proving?

2 years ago
For several decades people have tried to write computer programs that can find proofs of mathematical statements. There have been some notable successes, such as a computer-discovered proof of the Robbins conjecture, which had previously been an open problem. But in general, progress has been disappointing: many problems that are well within the reach of […]
Towards Understandable Neural Networks for High Level AI Tasks – Part 3

Towards Understandable Neural Networks for High Level AI Tasks – Part 3

2 years ago
Towards understandable neural networks for high level AI tasks – Part III Overview of talk series: Current AI software relies increasingly on neural networks (NNs). The universal data structure of NNs is the numerical vector of activity levels of model neurons, typically with activity distributed widely over many neurons. Can NNs in principle achieve human-like […]
Studio99 Presents: Michael Gough and “Drawing as Literacy.”

Studio99 Presents: Michael Gough and “Drawing as Literacy.”

2 years ago
Please help us welcome Michael Gough to Microsoft Research’s studio99. Michael is corporate vice president of design for Microsoft’s Applications and Services Group. He’ll be talking about Drawing as Literacy – why drawing is key to creativity and to using one’s whole brain.
Towards Cross-fertilization Between Propositional Satisfiability and Data Mining

Towards Cross-fertilization Between Propositional Satisfiability and Data Mining

2 years ago
In this talk, we overview our contribution to data mining and more generally to the cross-fertilization between data mining and propositional satisfiability (www.cril.univ-artois.fr/decMining/). We will focus on two contributions. First, we show how propositional satisfiability can be used to model and solve problems in data mining. As an illustration, we present a SAT-based declarative approach […]