开课单位--康奈尔大学

11
Convergent Learning: Do different neural networks learn the same representations?[收敛学习:不同的神经网络学习相同的表示吗?]
   Jason Yosinski(康奈尔大学) Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such resear...
热度:37

12
Understanding User Sensemaking in Machine Learning Fairness Assessment Systems[理解机器学习公平性评估系统中的用户感知]
  Jing Nathan Yan(康奈尔大学) Understanding User Sensemaking in Machine Learning Fairness Assessment Systems
热度:30

13
Random Graphs with Prescribed K-Core Sequences: A New Null Model for Network Analysis[具有规定K核序列的随机图:一种新的网络分析零模型]
  Katherine Van Koevering(康奈尔大学) Random Graphs with Prescribed K-Core Sequences: A New Null Model for Network Analysis
热度:31

14
On the Interplay between Social and Topical Structure[论社会结构与主题结构的相互作用]
   Chenhao Tan(康奈尔大学) People’s interests and people’s social relationships are intuitively connected, but understanding their interplay and whether they can hel...
热度:56

15
Scene Chronology[场景年表]
   Kevin Matzen(康奈尔大学) We present a new method for taking an urban scene reconstructed from a large Internet photo collection and reasoning about its change in appearance th...
热度:30

16
On Feature Selection, Bias-Variance, and Bagging[特征选择、偏差方差和装袋]
  M. Arthur Munson(康奈尔大学) We examine the mechanism by which feature selection improves the accuracy of supervised learning. An empirical bias/variance analysis as feature selec...
热度:32

17
Challenges for AI in Computational Sustainability[人工智能在计算的可持续性方面面临的挑战]
  Carla P. Gomes(康奈尔大学) **//Disclaimer:// VideoLectures.NET emphasizes that the quality of this video was notably improved, because of poor sound quality conditions provided ...
热度:29

18
Dynamic Ranked Retrieval[动态排名检索]
  Thorsten Joachims(康奈尔大学) We present a theoretically well-founded retrieval model for dynamically generating rankings based on interactive user feedback. Unlike conventional ra...
热度:61

19
Trade-Offs in Sampling-Based Adversarial Planning[基于抽样的对抗规划中的权衡 ]
  Raghuram Ramanujan(康奈尔大学) The Upper Confidence bounds for Trees (UCT) algorithm has in recent years captured the attention of the planning and game-playing community due to its...
热度:38

20
Attention By Proxy? Issues in Audience Awareness for Webcasts to Distributed Groups[注意代理?分布式网络广播的受众意识问题]
  Jeremy Birnholtz(康奈尔大学) Presents findings from a study of how classroom instructors pay attention to their students, and implications for displaying images of remote particip...
热度:47