Building Literate Machines with Dr. Adam Trischler
Episode 16 | March 21, 2018 Dr.
1 255
31.8
Microsoft Soundscape: A Map Delivered in 3D Sound [Audio Description]
“Soundscape fills in a lot of the mental map as you move, making it effortless and seamless to know what’s around you,” highlights Erin Lauridsen of Lighthouse for the Blind in San Francisco.
3 003
30
State-of-the-Art in Speech Technologies
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
4 868
16.6
Microsoft Research India Overview
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
8 268
23.4
State of Unsupervised Learning
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
2 732
23
Deep Learning: A Review
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
2 262
16.8
Tight Learning Bounds for Multi-Class Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 851
76.7
Protecting Sensitive User Data in Web Services
Web services like Google, Facebook, and Dropbox are now an essential part of people’s lives.
1 301
108.1
On Characterizing the Capacity of Neural Networks using Algebraic Topology
The learnability of different neural architectures can be characterized directly by computable measures of data complexity.
12 654
11.6
Augmenting Visualization Tools with Automated Design & Recommendation
Visualization is a critical tool for data science. Analysts use plots to explore and understand distributions and relationships in their data.
2 638
21.6
Fireside Chat with Yoshua Bengio
Interview between Susan Dumais and Yoshua Bengio. See more at microsoft.com/en-us/research/videos/ai-distinguished-lecture-series
3 934
17.1
Dense Associative Memories and Deep Learning
Dense Associative Memories are generalizations of Hopfield nets to higher order (higher than quadratic) interactions between the spins/neurons.
5 568
21.5
Quadratic Assignment on Different Data Models
Quadratic assignment is a very general problem in theoretical computer science.
3 945
62.3
Design and Evaluation of Effective, Interactive, and Interpretable Machine Learning
Machine learning is ubiquitous in domains such as criminal justice, credit, lending, and medicine.
1 388
57.5
Avoiding the Pitfalls of Active Learning with Robust Predictors for Covariate Shift
Pool-based active learning promises to significantly reduce the labeling burden of black-box supervised machine learning methods but often doesn't deliver in practice.
2 163
42.1
The Future of Voice
Perception doesn’t necessarily match reality when it comes to today’s voice user interfaces.
2 772
24.6
A Unifying Theory of First-Order Methods and Applications
First-order methods in optimization have become the workhorse tool in modern data-driven applications.
2 281
34.2
Bridging the Gap Between Theory and Practice in Machine Learning
Machine learning has become one of the most exciting research areas in the world, with various applications. However, there exists a noticeable gap between theory and practice.
4 614
19.6
Dreaming Contextual Memory
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 845
40.6
Extreme Classification in Healthcare
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
2 161
55.1
Deep Learning Approach for Extreme Multi-label Text Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
24 384
41.8
A Parallel Primal-Dual Sparse Method for Extreme Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 395
66
EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 161
128.7
Extreme Multi-label Learning via Nearest Neighbor Graph Partitioning and Embedding
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
3 791
46.5
Microsoft Hands-Free Music
Our mission is to restore critical expressive & creative channels for people severely affected by disabling conditions, such as ALS, spinal cord injury, and related conditions with potential to
3 217
118.8
Deep Attention Mechanism for Multimodal Intelligence: Perception, Reasoning, & Expression
We have long envisioned that machines one day can perform human-like perception, reasoning, and expression across multiple modalities including vision and language, which will augment and transform
2 614
43.2
The Four Big Bets (Illustrated via a Journey in Program Synthesis)
Sumit Gulwani will talk about the four bets that he made in the second half of his research career, which yielded greater personal satisfaction.
3 241
22.2
Fast Algorithms via Convex Relaxation
In Theoretical CS many of the fastest algorithms are obtained by considering the Linear Programming (LP) relaxation of the problem.
2 082
49.2
CLAW: A Multifunctional Handheld Haptic Controller for Grasping, Touching, and Triggering in VR
CLAW extends the concept of a VR controller to a multifunctional haptic tool, using a single motor. At first glance, it looks very similar to your standard VR controller.
44 994
59.4
Haptic Revolver: Touch, Shear, Texture, & Shape Rendering on a Reconfigurable VR Controller
The Haptic Revolver, also known as the Haptic Wheel, uses an actuated wheel that moves up and down to render touch contact with a virtual surface and spins to render shear forces and motion as the
10 349
39.3