开课单位--纽约大学

31
A Factor Model for Learning Higher Order Features in Natural Images[自然图像中学习高阶特征的一个因子模型]
  Yan Karklin(纽约大学) The visual system is a hierarchy of processing stages. Each stage in this pathway, in addition to encoding increasingly complex features of the input,...
热度:48

32
Principal Component and the Long Run[主成分和长期运行]
  Xiaohong Chen(纽约大学) 主成分和长期运行
热度:26

33
Tightening LP Relaxations for MAP using Message Passing[收紧线性规划松弛用于地图使用消息传递]
  David Sontag(纽约大学) Linear Programming (LP) relaxations have become powerful tools for finding the most probable (MAP) configuration in graphical models. These relaxat...
热度:51

34
A Comprehensive Model of All Astronomical Imaging Ever Taken[一种全天文成像的综合模型]
  David W. Hogg(纽约大学) In astrophysics we are beginning to work with extremely large data sets. However, unlike in most other data-science domains, we have a reasonable hand...
热度:25

35
Theories of Everything[万有理论 ]
  David W. Hogg(纽约大学) Cosmology, at the present day, works with static catalogs (of, say, galaxies) and point estimates of fundamental physical quantities (of, for example,...
热度:30

36
Patient Surveillance Algorithms for the Emergency Department[急诊科病人监控算法 ]
  Yonatan Halpern(纽约大学) Physicians in the emergency department must rapidly gather and synthesize large amounts of data from disparate sources in order to make treatment deci...
热度:41

37
A blind deconvolution method for neural spike identification[一种用于神经突点识别的盲反褶积方法]
  Chaitanya Ekanadham(纽约大学) We consider the problem of estimating neural spikes from extracellular voltage recordings. Most current methods are based on clustering, which require...
热度:50

38
Complexity of Inference in Latent Dirichlet Allocation[潜在狄利克雷分配中推理的复杂性]
  David Sontag(纽约大学) We consider the computational complexity of probabilistic inference in Latent Dirichlet Allocation (LDA). First, we study the problem of finding the m...
热度:71

39
Reinforcement Learning in Humans and Other Animals[加强人类和其他动物的学习]
  Nathaniel Daw(纽约大学) Algorithms from computer science can serve as detailed process-level hypotheses for how the brain might approach difficult information processing prob...
热度:45

40
Semi-Supervised Learning in Gigantic Image Collections[大型图像采集中的半监督学习]
  Rob Fergus(纽约大学) With the advent of the Internet it is now possible to collect hundreds of millions of images. These images come with varying degrees of label informat...
热度:44