开课单位--蒙特利尔大学
11
12
13
14
15
16
17
18
19
20
![](functions/showpic.php?filename=2020060902025716.jpg)
Scaling Up Deep Learning[扩大深度学习]
Yoshua Bengio(蒙特利尔大学) Deep learning has rapidly moved from a marginal approach in the machine learning community less than ten years ago to one that has strong industrial i...
热度:44
Yoshua Bengio(蒙特利尔大学) Deep learning has rapidly moved from a marginal approach in the machine learning community less than ten years ago to one that has strong industrial i...
热度:44
![](functions/showpic.php?filename=2016012501291883.png)
Extracting and Composing Robust Features with Denoising Autoencoders[具有去噪的自动编码器的提取与组合鲁棒特征]
Pascal Vincent(蒙特利尔大学) Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning...
热度:64
Pascal Vincent(蒙特利尔大学) Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning...
热度:64
![](functions/showpic.php?filename=2016060302415049.png)
A Preliminary Evaluation of Word Representations for Named-Entity Recognition[命名实体识别的一个字表示的初步评价]
Joseph Turian(蒙特利尔大学) We use different word representations as word features for a named-entity recognition (NER) system with a linear model. This work is part of a larger ...
热度:39
Joseph Turian(蒙特利尔大学) We use different word representations as word features for a named-entity recognition (NER) system with a linear model. This work is part of a larger ...
热度:39
![](functions/showpic.php?filename=2016052903145921.png)
Learning Deep Hierarchies of Representations[学习表述的深层次体系]
Yoshua Bengio;Samy Bengio(蒙特利尔大学) Whereas theoretical work suggests that deep architectures might be computationally and statistically more efficient at representing highly-varying fun...
热度:22
Yoshua Bengio;Samy Bengio(蒙特利尔大学) Whereas theoretical work suggests that deep architectures might be computationally and statistically more efficient at representing highly-varying fun...
热度:22
![](functions/showpic.php?filename=2020033009064181.jpg)
Tutorial on Learning Deep Architectures[学习深层架构教程]
Yoshua Bengio; Yann LeCun(蒙特利尔大学) This short tutorial on deep learning will review a variety of methods for learning multi-level, hierarchical representations, emphasizing their common...
热度:35
Yoshua Bengio; Yann LeCun(蒙特利尔大学) This short tutorial on deep learning will review a variety of methods for learning multi-level, hierarchical representations, emphasizing their common...
热度:35
![](functions/showpic.php?filename=2016101206350258.png)
The Neural Autoregressive Distribution Estimator, incl. discussion by Yoshua Bengio[神经自回归分布估计,以及Yoshua Bengio的相关讨论]
Yoshua Bengio;Hugo Larochelle(蒙特利尔大学) We describe a new approach for modeling the distribution of high-dimensional vectors of discrete variables. This model is inspired by the restricted B...
热度:92
Yoshua Bengio;Hugo Larochelle(蒙特利尔大学) We describe a new approach for modeling the distribution of high-dimensional vectors of discrete variables. This model is inspired by the restricted B...
热度:92
![](functions/showpic.php?filename=2017031102512699.jpg)
Metropolis-Hastings Sampling in a FilterBoost Music Classifier[大都市黑斯廷斯采样在filterboost音乐分类]
Thierry Bertin-Mahieux(蒙特利尔大学)
热度:30
Thierry Bertin-Mahieux(蒙特利尔大学)
热度:30
![](functions/showpic.php?filename=2019072603595388.png)
Manifold Tangent Classifier[流形切线分级机]
Yann Dauphin(蒙特利尔大学) We combine three important ideas present in previous work for building classifiers: the semi-supervised hypothesis (the input distribution contains in...
热度:30
Yann Dauphin(蒙特利尔大学) We combine three important ideas present in previous work for building classifiers: the semi-supervised hypothesis (the input distribution contains in...
热度:30
![](functions/showpic.php?filename=2019051608334993.jpg)
Book-Adaptive and Book-Dependent Models to Accelerate Digitization of Early Music[书籍自适应和书籍依赖模型加速早期音乐的数字化]
Douglas Eck(蒙特利尔大学) Optical music recognition (OMR) enables early music collections to be digitized on a large scale. The workflow for such digitisation projects also inc...
热度:36
Douglas Eck(蒙特利尔大学) Optical music recognition (OMR) enables early music collections to be digitized on a large scale. The workflow for such digitisation projects also inc...
热度:36
![](functions/showpic.php?filename=2019042110572020.png)
Tutorial on Learning Deep Architectures[学习深层架构的教程]
Yann LeCun, Yoshua Bengio(蒙特利尔大学) This short tutorial on deep learning will review a variety of methods for learning multi-level, hierarchical representations, emphasizing their common...
热度:29
Yann LeCun, Yoshua Bengio(蒙特利尔大学) This short tutorial on deep learning will review a variety of methods for learning multi-level, hierarchical representations, emphasizing their common...
热度:29