开课单位--华盛顿大学
11
12
Creating Infinitely Adaptable Courseware[创建无限适应性课件]
Zoran Popović(华盛顿大学) What does it take to create an infinitely adaptable courseware that creates optimal learning pathways for each student? Such courseware needs to have ...
热度:33
Zoran Popović(华盛顿大学) What does it take to create an infinitely adaptable courseware that creates optimal learning pathways for each student? Such courseware needs to have ...
热度:33
13
On combining graph-based variance reduction schemes[基于组合图的方差缩减方案研究]
Vibhav Gogate(华盛顿大学) In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-c...
热度:38
Vibhav Gogate(华盛顿大学) In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-c...
热度:38
14
Is Deep Learning the New 42?[深度学习是新的42吗?]
Pedro Domingos(华盛顿大学) The history of deep learning goes back more than five decades but in the marketplace of ideas its perceived value went through booms and busts. We are...
热度:37
Pedro Domingos(华盛顿大学) The history of deep learning goes back more than five decades but in the marketplace of ideas its perceived value went through booms and busts. We are...
热度:37
15
Fast Flux Discriminant for Large-Scale Sparse Nonlinear Classification[大规模稀疏非线性分类的快速流量判别法]
Wenlin Chen(华盛顿大学) In this paper, we propose a novel supervised learning method, Fast Flux Discriminant (FFD), for large-scale nonlinear classification. Compared with ot...
热度:42
Wenlin Chen(华盛顿大学) In this paper, we propose a novel supervised learning method, Fast Flux Discriminant (FFD), for large-scale nonlinear classification. Compared with ot...
热度:42
16
A Naturalistic Open Source Movie for Optical Flow Evaluation[用于光流评估的自然开源电影]
Daniel J. Butler(华盛顿大学) Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of s...
热度:61
Daniel J. Butler(华盛顿大学) Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of s...
热度:61
17
Machine Learning for the Web: A Unified View[Web机器学习:统一视图]
Pedro Domingos(华盛顿大学) Machine learning and the Web are a technology and an application area made for each other. The Web provides machine learning with an ever-growing stre...
热度:47
Pedro Domingos(华盛顿大学) Machine learning and the Web are a technology and an application area made for each other. The Web provides machine learning with an ever-growing stre...
热度:47
18
Information Arbitrage Across Multi-lingual Wikipedia[跨语言维基百科的信息套利]
Daniel S. Weld;Michael Skinner;Eytan Adar(华盛顿大学) Information Arbitrage Across Multi-lingual Wikipedia
热度:45
Daniel S. Weld;Michael Skinner;Eytan Adar(华盛顿大学) Information Arbitrage Across Multi-lingual Wikipedia
热度:45
19
Collaboration Over Time: Characterizing and Modeling Network Evolution.[随着时间的推移协作:网络演化的特征和建模。 ]
Jian Huang(华盛顿大学) Collaboration Over Time: Characterizing and Modeling Network Evolution.
热度:59
Jian Huang(华盛顿大学) Collaboration Over Time: Characterizing and Modeling Network Evolution.
热度:59
20
Multi-way Gaussian Graphical Models with Application to Multivariate Lattice Data[多元高斯图模型及其在多元格子数据中的应用]
Adrian Dobra(华盛顿大学) The literature on Gaussian graphical models (GGMs) contains two equally rich and equally significant domains of research efforts and interests. The fi...
热度:56
Adrian Dobra(华盛顿大学) The literature on Gaussian graphical models (GGMs) contains two equally rich and equally significant domains of research efforts and interests. The fi...
热度:56