图 书 馆开课单位--纽约大学
21
22
23
24
25
26
27
28
29
30
2113th European Conference on Computer Vision (ECCV), Zurich 2014 [可视化和理解卷积网络]
Matthew Zeiler(纽约大学) Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. ...
热度：35
Matthew Zeiler(纽约大学) Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. ...
热度：35
22Learning to See in the Dark: The Roots of Ethical Resistance[学会在黑暗中看：道德抵抗的根源]
Carol Gilligan(纽约大学) In this complex narrative documenting paradigm shifts in developmental thinking, Carol Gilligan defines the very capacity of our human nature—to...
热度：31
Carol Gilligan(纽约大学) In this complex narrative documenting paradigm shifts in developmental thinking, Carol Gilligan defines the very capacity of our human nature—to...
热度：31
23Revisiting Globally Sorted Indexes for Efficient Document Retrieval[重温全球排序指标的有效的文献检索]
Hao Yan(纽约大学) There has been a large amount of research on efficient document retrieval in both IR and web search areas. One important technique to improve retrieva...
热度：28
Hao Yan(纽约大学) There has been a large amount of research on efficient document retrieval in both IR and web search areas. One important technique to improve retrieva...
热度：28
2425Learning Convolutional Feature Hierarchies for Visual Recognition[学习卷积特征层次的视觉识别]
Y-Lan Boureau(纽约大学) We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features. While sparse coding has become an increasingl...
热度：39
Y-Lan Boureau(纽约大学) We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features. While sparse coding has become an increasingl...
热度：39
26More data means less inference: A pseudo-max approach to structured learning[更多的数据意味着更少的推理：一个伪最大的方法来结构化学习]
David Sontag(纽约大学) The problem of learning to predict structured labels is of key importance in many applications. However, for general graph structure both learning and...
热度：27
David Sontag(纽约大学) The problem of learning to predict structured labels is of key importance in many applications. However, for general graph structure both learning and...
热度：27
27Building Resilient Infrastructure to Combat Terrorism: Lessons from September 11th[建设弹性基础设施来打击恐怖主义：来自9月11日的教训]
Rae Zimmerman(纽约大学) Building Resilient Infrastructure to Combat Terrorism: Lessons from September 11th
热度：30
Rae Zimmerman(纽约大学) Building Resilient Infrastructure to Combat Terrorism: Lessons from September 11th
热度：30
28Who is Afraid of Non-Convex Loss Functions?[谁怕损失非凸函数？]
Yann LeCun(纽约大学) The NIPS community has suffered of an acute convexivitis epidemic: - ML applications seem to have trouble moving beyond logistic regression, SV...
热度：38
Yann LeCun(纽约大学) The NIPS community has suffered of an acute convexivitis epidemic: - ML applications seem to have trouble moving beyond logistic regression, SV...
热度：38
29Interview with Yann LeCun[采访 Yann LeCun]
Yann LeCun(纽约大学) His lab has projects in computer vision, object detection, object recognition, mobile robotics, bio-informatics, biological image analysis, medical si...
热度：40
Yann LeCun(纽约大学) His lab has projects in computer vision, object detection, object recognition, mobile robotics, bio-informatics, biological image analysis, medical si...
热度：40
30Autonomously Adapting Range Data Patterns for Object Detection[用于目标检测的范围自适应数据模式]
Theodoros Varvadoukas(纽约大学) We present a novel approach to recognizing patterns in laser range data that performs on a par with the state of the art while at the same requiring m...
热度：50
Theodoros Varvadoukas(纽约大学) We present a novel approach to recognizing patterns in laser range data that performs on a par with the state of the art while at the same requiring m...
热度：50