开课单位--芝加哥丰田技术学院
1
2
3
4
5
6
7
8
9
10
![](functions/showpic.php?filename=2017031908415552.jpg)
Online Learning and Game Theory[在线学习与博弈论]
Adam Kalai(芝加哥丰田技术学院) We consider online learning and its relationship to game theory. In an online decision-making problem, as in Singer's lecture, one typically makes...
热度:40
Adam Kalai(芝加哥丰田技术学院) We consider online learning and its relationship to game theory. In an online decision-making problem, as in Singer's lecture, one typically makes...
热度:40
![](functions/showpic.php?filename=2016112508184230.png)
Continuous Markov Random Fields for Robust Stereo Estimation[用于鲁棒立体声预估的马尔科夫连续随机场]
Laurent Itti;Koichiro Yamaguchi; Ramin Zabih(芝加哥丰田技术学院) In this paper we present a novel slanted-plane model which reasons jointly about occlusion boundaries as well as depth. We formulate the problem as on...
热度:51
Laurent Itti;Koichiro Yamaguchi; Ramin Zabih(芝加哥丰田技术学院) In this paper we present a novel slanted-plane model which reasons jointly about occlusion boundaries as well as depth. We formulate the problem as on...
热度:51
![](functions/showpic.php?filename=2020092502392214.png)
Factoring Speech into Linguistic Features[语音分解成语言特点]
Karen Livescu(芝加哥丰田技术学院) Spoken language technologies, such as automatic speech recognition and synthesis, typically treat speech as a string of "phones". In contras...
热度:53
Karen Livescu(芝加哥丰田技术学院) Spoken language technologies, such as automatic speech recognition and synthesis, typically treat speech as a string of "phones". In contras...
热度:53
![](functions/showpic.php?filename=2016060911262428.png)
Regularization Strategies and Empirical Bayesian Learning for MKL[MKL的正则化策略和贝叶斯经验学习]
Ryota Tomioka(芝加哥丰田技术学院) Multiple kernel learning (MKL) has received considerable attention recently. In this paper, we show how different MKL algorithms can be understood as ...
热度:48
Ryota Tomioka(芝加哥丰田技术学院) Multiple kernel learning (MKL) has received considerable attention recently. In this paper, we show how different MKL algorithms can be understood as ...
热度:48
![](functions/showpic.php?filename=2015110903405820.jpg)
SVM Optimization: Inverse Dependence on Training Set Size[支持向量机优化:对训练集大小的逆依赖]
Nathan Srebro(芝加哥丰田技术学院) We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical result...
热度:84
Nathan Srebro(芝加哥丰田技术学院) We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical result...
热度:84
![](functions/showpic.php?filename=2015112810435331.png)
Graphical Models for Speech Recognition: Articulatory and Audio-Visual Models[语音识别的图形化模型:发音和音频视觉模型]
Karen Livescu(芝加哥丰田技术学院) Since the 1980s, the main approach to automatic speech recognition has been using hidden Markov models (HMMs), in which each state corresponds to a ph...
热度:59
Karen Livescu(芝加哥丰田技术学院) Since the 1980s, the main approach to automatic speech recognition has been using hidden Markov models (HMMs), in which each state corresponds to a ph...
热度:59
![](functions/showpic.php?filename=2015112810133564.png)
Training Structured Predictors for Novel Loss Functions[新的损失函数的训练结构的预测]
David McAllester(芝加哥丰田技术学院) As a motivation we consider the PASCAL image segmentation challenge. Given an image and a target class, such as person, the challenge is to segment th...
热度:64
David McAllester(芝加哥丰田技术学院) As a motivation we consider the PASCAL image segmentation challenge. Given an image and a target class, such as person, the challenge is to segment th...
热度:64
![](functions/showpic.php?filename=2015111407372646.jpg)
On Multilabel Classification and Ranking with Partial Feedback[细粒度的分类和部分反馈的排名]
Francesco Orabona(芝加哥丰田技术学院) We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and reli...
热度:39
Francesco Orabona(芝加哥丰田技术学院) We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and reli...
热度:39
![](functions/showpic.php?filename=2015122009400864.png)
The Projectron: a Bounded Kernel-Based Perceptron[一个有界的projectron:基于核感知器]
Francesco Orabona(芝加哥丰田技术学院) We present a discriminative online algorithm with a bounded memory growth, which is based on the kernel-based Perceptron. Generally, the required memo...
热度:86
Francesco Orabona(芝加哥丰田技术学院) We present a discriminative online algorithm with a bounded memory growth, which is based on the kernel-based Perceptron. Generally, the required memo...
热度:86
![](functions/showpic.php?filename=2016022303414815.png)
Online-Batch Strongly Convex Multi Kernel Learning[在线批量强凸多核学习]
Francesco Orabona(芝加哥丰田技术学院) Several object categorization algorithms use kernel methods over multiple cues, as they offer a principled approach to combine multiple cues, and to o...
热度:44
Francesco Orabona(芝加哥丰田技术学院) Several object categorization algorithms use kernel methods over multiple cues, as they offer a principled approach to combine multiple cues, and to o...
热度:44