开课单位--微软公司

111
A Spectral Algorithm for Latent Dirichlet Allocation[一种潜在dirichlet分配谱算法]
  Daniel Hsu(微软公司) Topic modeling is a generalization of clustering that posits that observations (words in a document) are generated by \emph{multiple} latent factors (...
热度:48

112
Hierarchical sampling for active learning[主动学习的分层抽样]
  Daniel Hsu(微软公司) We present an active learning scheme that exploits cluster structure in data.
热度:61

113
Practical Guide to Controlled Experiments on the Web: Listen to Your Customers not to the HiPPO [网上受控实验实用指南:倾听客户的意见,而不是HiPPO]
  Ron Kohavi(微软公司) The web provides an unprecedented opportunity to evaluate ideas quickly using controlled experiments, also called randomized experiments (single-facto...
热度:55

114
Selecting Diverse Features via Spectral Regularization[通过光谱正则化选择不同的特征]
  Abhimanyu Das(微软公司) We study the problem of diverse feature selection in linear regression: selecting a small subset of diverse features that can predict a given objectiv...
热度:51

115
Embracing Uncertainty: Applied Machine Learning Comes of Age[拥抱不确定性:应用机器学习成为时代]
  Christopher Bishop(微软公司) Over the last decade the number of deployed applications of machine learning has grown rapidly, with examples in domains ranging from recommendation s...
热度:35

116
Detecting Text in Natural Scenes with Stroke Width Transform[用笔画宽度变换检测自然场景中的文本]
  Boris Epshtein(微软公司) We present a novel image operator that seeks to find the value of stroke width for each image pixel, and demonstrate its use on the task of text detec...
热度:107

117
Cloud computing: A productivity opportunity, a policy challenge!?[云计算:生产力机遇,政策挑战!]
  Wilfried Grommen(微软公司) Cloud computing, or software services on the internet are “the” new wave in computing. This is the natural evolution of ICT towards a util...
热度:29

118
Oracle inequalities for computationally budgeted model selection[用于计算预算模型选择的Oracle不等式]
  Alekh Agarwal(微软公司) We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selec...
热度:177

119
Sample Complexity Bounds for Differentially Private Learning[个体差异学习的样本复杂性界限]
  Daniel Hsu(微软公司) We study the problem of privacy-preserving classification – namely, learning a classifier from sensitive data, while still preserving the privac...
热度:59

120
Incompatibilities between PAC-Bayes and Exploration[PAC贝叶斯和勘探之间的不兼容性]
  John Langford(微软公司) author: John Langford, Microsoft Research published: April 14, 2010,   recorded: March 2010,   views: 100 Categories Top » Comput...
热度:36