22.06.16 1:04:35 Intelligible Machine Learning Models for HealthCare
In machine learning often a tradeoff must be made between accuracy and intelligibility: the most accurate models usually are not very intelligible (e.g., random forests, boosted trees, and neural
2 065
28.3
22.06.16 17:21 An evolutionary view on information processing in cells
An evolutionary view on information processing in cells
91
22.06.16 1:37:06 Online Learning and Bandits - Part 1
The ability to make continual, accurate decisions based on evolving data is key in many of today's data-driven intelligent systems.
3 906
46.1
22.06.16 23:00 X1-Locally Non-linear Embeddings for Extreme Multi-label Learning
X1-Locally Non-linear Embeddings for Extreme Multi-label Learning
233
22.06.16 1:43:19 Large-scale Linear and Kernel Classification - Part 2
Linear and kernel methods are important machine learning techniques for data classification. Popular examples include support vector machines (SVM) and logistic regression.
153
22.06.16 1:26:35 Submodular Optimization and Machine Learning - Part 1
Many problems in machine learning that involve discrete structures or subset selection may be phrased in the language of submodular set functions.
4 569
37.7
22.06.16 1:36:24 Large-scale Linear and Kernel Classification - Part 1
Linear and kernel methods are important machine learning techniques for data classification. Popular examples include support vector machines (SVM) and logistic regression.
496
54.8
22.06.16 55:46 Probability and Prejudice: Bridging the Gap Between Machine Learning and Programming Languages
Probabilistic programming languages are often thought of as a point of intersection between machine learning and programming languages.
147
22.06.16 14:48 Stan Future Plans
The goal of this workshop is to inform people about open source machine learning systems being developed, aid the coordination of such projects, and discuss future plans.
9
22.06.16 13:19 Shogun Future Plans
The goal of this workshop is to inform people about open source machine learning systems being developed, aid the coordination of such projects, and discuss future plans.
28
22.06.16 1:25:55 Submodular Optimization and Machine Learning - Part 2
Many problems in machine learning that involve discrete structures or subset selection may be phrased in the language of submodular set functions.
534
35.3
22.06.16 1:03:02 Active Learning and Annotation
The "active learning" model is motivated by scenarios in which it is easy to amass vast quantities of unlabeled data (images and videos off the web, speech signals from microphone recordings, and so
10 122
21.1
22.06.16 9:10 Vowpal Wabbit Future Plans
The goal of this workshop is to inform people about open source machine learning systems being developed, aid the coordination of such projects, and discuss future plans.
515
56.9
22.06.16 1:00:32 Fast and Simple Algorithms for Constrained Submodular Maximization
Submodular maximization captures both classical problems in combinatorial optimization and recent more practical applications that arise in other disciplines, e.g., machine learning and data mining.
291
22.06.16 54:22 Manifold correspondence: a signal processing perspective
In recent years, geometric data is gaining increasing interest both in the academia and industry.
637
20.9
22.06.16 1:37:50 Distributed Machine Learning Algorithms: Communication-Computation Trade-offs - Part 1
Distributed machine learning is an important area that has been receiving considerable attention from academic and industrial communities, as data is growing in unprecedented rate.
1 017
48
22.06.16 1:38:38 Reinforcement Learning: An Introduction
Distributed machine learning is an important area that has been receiving considerable attention from academic and industrial communities, as data is growing in unprecedented rate.
3 559
27.9
22.06.16 1:31:53 MSR India Research Overview
Distributed machine learning is an important area that has been receiving considerable attention from academic and industrial communities, as data is growing in unprecedented rate.
900
29.7
22.06.16 1:23:09 Mathematica Tech Talk with Wolfram
During this seminar, we will explore using Mathematica and the Wolfram Cloud for a wide variety of practical applications in R and D.
232
22.06.16 57:34 Near Optimal LP Rounding for Correlation Clustering on Complete Graphs
Introduced about 10 years ago by Bansal, Blum and Chawla, correlation clustering has become one of the standard techniques in machine learning and data mining.
485
26.6
22.06.16 1:22:02 Standing on the Shoulders of a Giant: One Person’s Experience of Turing’s Impact
After saying something about the recent movie, “The Imitation Game” (these days, one can’t talk about Alan Turing without doing so…), I will describe three of Alan Turing’s major achievements, in
27
22.06.16 55:40 UW - MSR Machine Learning workshop 2015 - Session 4
14:15Commonsense, Vision and Language - Larry Zitnick The recent significant advances in computer vision, natural language processing and other related areas has led to a renewed interest in
323
22.06.16 1:09:57 Scaling Up Reinforcement Learning
Distributed machine learning is an important area that has been receiving considerable attention from academic and industrial communities, as data is growing in unprecedented rate.
221
22.06.16 18:07 Debugging Machine Learning Tasks with PSI
Machine learning applications are ubiquitous in classification, recognition, filtering, recommendation, and many other domains.
386
128.3
22.06.16 1:14:49 Human-Robot Collaboration
In order for robots to collaborate with humans, they must infer helpful actions in the physical world by observing the human's language, gesture, and actions.
2 239
35.2
22.06.16 1:02:22 Distributed Machine Learning Algorithms: Communication-Computation Trade-offs - Part 2
Distributed machine learning is an important area that has been receiving considerable attention from academic and industrial communities, as data is growing in unprecedented rate.
563
187.3
22.06.16 1:05:53 Multimodal Learning from Bespoke Data
Big Data and Deep Learning have rightly received a lot of attention, since their combination has led to breakthroughs in performance on some very hard problems.
384
42.3
22.06.16 22:44 Human-centric machine learning.
How can we enable a human being to carry out machine learning that is of value to themselves and to others?
149
22.06.16 26:25 Tree Structured Gaussian Process Approximations.
Gaussian process regression can be accelerated by constructing a small pseudo-dataset to summarize the observed data.
883
32.3
22.06.16 1:26:23 Online Learning and Bandits - Part 2
The ability to make continual, accurate decisions based on evolving data is key in many of today's data-driven intelligent systems.
710
26