Symposium: Deep Learning - Max Jaderberg
Spatial Transformer Networks - Max Jaderberg
5 862
18.8
Welcome and Keynote - Geoff Bilder, Director of Strategic Initiatives at CrossRef
If we funded and ran physical infrastructure the way we fund and run scholarly cyberinfrastructure, the lights and water would go out every grant cycle and we would have architects bidding to build
161
Keynote - A Better Way to Deliver Innovation?
In the closing keynote for Faculty Summit 2015, Peter Lee, corporate vice president of Microsoft Research, explores the topic of better ways to deliver innovation.
291
Panel 1 - Capturing the Research Lifecycle
Chair: Courtney Soderberg, Statistical Consultant at the Center for Open Science, will lead a panel discussion of the challenges associated with organizing research data, disseminating and
45
Invited Talks: Computational Principles for Deep Neuronal Architectures
Invited Talks: Computational Principles for Deep Neuronal Architectures.
353
58.5
Approximate Majority algorithm
A distributed algorithm for computing the majority between two populations.
918
152.7
Symposium: Brains, Minds and Machines - Joshua Tenenbaum
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?
2 110
19.2
Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming
Gaming on phones, tablets and laptops is very popular.
1 384
17.4
Provable Algorithms for Learning Neural Networks
We study the learning of fully connected neural networks for binary classification.
421
34.8
Modern Deep Learning through Bayesian Eyes
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.
5 890
22.2
Towards Understandable Neural Networks for High Level AI Tasks; Part 2
Towards Understandable Neural Networks for High Level AI Tasks; Part 2.
204
Towards Understandable Neural Networks for High Level AI Tasks - Part 4
Overview of talk series: Current AI software relies increasingly on neural networks (NNs).
188
What are the prospects for automatic theorem proving?
For several decades people have tried to write computer programs that can find proofs of mathematical statements.
9 993
14.2
Towards Understandable Neural Networks for High Level AI Tasks - Part 3
Towards understandable neural networks for high level AI tasks - Part III Overview of talk series: Current AI software relies increasingly on neural networks (NNs).
197
Artist in Residence (formerly Studio99) Presents: Michael Gough and "Drawing as Literacy."
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.
269
Towards Cross-fertilization Between Propositional Satisfiability and Data Mining
In this talk, we overview our contribution to data mining and more generally to the cross-fertilization between data mining and propositional satisfiability (
72
Making Objects Count: A Shape Analysis Framework for Proving Polynomial Time Termination
We present a novel technique for verifying that (recursive) heap manipulating programs terminate in polynomial time.
86
Human factors of software updates
Many people delay or completely avoid updating the software on their devices. This can cause serious issues for security and software management.
318
20.7
Machine-Checked Correctness and Complexity of a Union-Find Implementation
Union-Find is a famous example of a simple data structure whose amortized asymptotic time complexity analysis is non-trivial.
332
55
Applications of 3-Dimensional Spherical Transforms to Acoustics and Personalization of Head-related
The spherical harmonic transform (SHT), which returns spatial frequency components of data or distributions determined on the unit sphere, has found many applications in acoustics, such as spatial
1 867
25.6
Network Protocols: Myths, Missteps, and Mysteries
In the field of computer networks, and undoubtedly in other engineering fields, a lot of what "everybody knows" is ... not true.
259
Optimal and Adaptive Online Learning
Online learning is one of the most important and well-established learning models in machine learning.
1 309
26.9
Speaker Diarization: Optimal Clustering and Learning Speaker Embeddings
Speaker diarization consist of automatically partitioning an input audio stream into homogeneous segments (segmentation) and assigning these segments to the same speaker (speaker clustering).
4 710
48.7
Multi-rate neural networks for efficient acoustic modeling
In sequence recognition, the problem of long-span dependency in input sequences is typically tackled using recurrent neural network architectures, and robustness to sequential distortions is
476
158.3
Unsupervised Latent Faults Detection in Data Centers
This talk will review our ongoing work on unsupervised latent fault detection in large scale data centers, such as those used cloud services, supercomputers, and compute clusters.
353
117.3