开课单位--德克萨斯大学
11
12
13
14
15
16
17
18
19
20
![](functions/showpic.php?filename=2020112606122932.png)
Practical RL: Representation, interaction, synthesis, and morality (PRISM)[实践RL:表现、互动、综合与道德(PRISM)]
Peter Stone(德克萨斯大学) When scaling up Reinforcement Learning (RL) to large continuous domains with imperfect representations and hierarchical structure, we often try applyi...
热度:45
Peter Stone(德克萨斯大学) When scaling up Reinforcement Learning (RL) to large continuous domains with imperfect representations and hierarchical structure, we often try applyi...
热度:45
![](functions/showpic.php?filename=2020120709575243.jpg)
Robust PCA and Collaborative Filtering: Rejecting Outliers, Identifying Manipulators[鲁棒PCA与协同过滤:剔除异常值,识别机械手]
Constantine Caramanis(德克萨斯大学) Principal Component Analysis is one of the most widely used techniques for dimensionality reduction. Nevertheless, it is plagued by sensitivity to out...
热度:38
Constantine Caramanis(德克萨斯大学) Principal Component Analysis is one of the most widely used techniques for dimensionality reduction. Nevertheless, it is plagued by sensitivity to out...
热度:38
![](functions/showpic.php?filename=2020121406063263.jpg)
Active learning of neural response functions with Gaussian processes[高斯过程神经响应函数的主动学习]
Mijung Park(德克萨斯大学) A sizable literature has focused on the problem of estimating a low-dimensional feature space capturing a neuron's stimulus sensitivity. However, ...
热度:30
Mijung Park(德克萨斯大学) A sizable literature has focused on the problem of estimating a low-dimensional feature space capturing a neuron's stimulus sensitivity. However, ...
热度:30
![](functions/showpic.php?filename=2020112507302950.png)
Graphical Models via Generalized Linear Models[基于广义线性模型的图形模型]
Eunho Yang(德克萨斯大学) Undirected graphical models, or Markov networks, such as Gaussian graphical models and Ising models enjoy popularity in a variety of applications. In ...
热度:54
Eunho Yang(德克萨斯大学) Undirected graphical models, or Markov networks, such as Gaussian graphical models and Ising models enjoy popularity in a variety of applications. In ...
热度:54
![](functions/showpic.php?filename=2020111207195132.png)
Focusing Human Attention on the "Right" Visual Data[把人类的注意力集中在“正确”的视觉数据上]
Kristen Grauman(德克萨斯大学) Widespread visual sensors and unprecedented connectivity have left us awash with visual data‐‐‐from online photo collections, home videos, news foo...
热度:35
Kristen Grauman(德克萨斯大学) Widespread visual sensors and unprecedented connectivity have left us awash with visual data‐‐‐from online photo collections, home videos, news foo...
热度:35
![](functions/showpic.php?filename=2020102806513319.png)
Words as reflections of psychological state[语言作为心理状态的反映]
James W. Pennebaker(德克萨斯大学) Pennebaker’s research explores the links between traumatic experiences, expressive writing, natural language use, and physical and mental health...
热度:45
James W. Pennebaker(德克萨斯大学) Pennebaker’s research explores the links between traumatic experiences, expressive writing, natural language use, and physical and mental health...
热度:45
![](functions/showpic.php?filename=2020110107525054.png)
Grounded Language Learning[扎根语言学习]
Raymond J. Mooney(德克萨斯大学) Most approaches to semantics in computational linguistics represent meaning in terms of words or abstract symbols. Grounded-language research bases th...
热度:122
Raymond J. Mooney(德克萨斯大学) Most approaches to semantics in computational linguistics represent meaning in terms of words or abstract symbols. Grounded-language research bases th...
热度:122
![](functions/showpic.php?filename=2019040207305868.png)
Multi-Subspace Representation and Discovery[多子空间表示和发现]
Chris Ding(德克萨斯大学) This paper presents the multi-subspace discovery problem and provides a theoretical solution which is guaranteed to recover the number of subspaces, t...
热度:75
Chris Ding(德克萨斯大学) This paper presents the multi-subspace discovery problem and provides a theoretical solution which is guaranteed to recover the number of subspaces, t...
热度:75
![](functions/showpic.php?filename=2019032707142552.png)
Integrating Novel Class Detection with Classification for Concept-Drifting Data Streams[将新颖的类检测与概念漂移数据流的分类相结合]
Latifur Khan(德克萨斯大学) In a typical data stream classification task, it is assumed that the total number of classes are fixed. This assumption may not be valid in a real str...
热度:66
Latifur Khan(德克萨斯大学) In a typical data stream classification task, it is assumed that the total number of classes are fixed. This assumption may not be valid in a real str...
热度:66
![](functions/showpic.php?filename=2018051407470988.jpg)