开课单位--蒙特利尔大学
123>>> 1/3

1
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention[显示、出席和讲述：具有视觉注意力的神经图像标题生成]
  Kelvin Xu(蒙特利尔大学) Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the c...
热度：25

2
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation[重组网络：从粗到细的特征聚合学习]
  Sina Honari(蒙特利尔大学) Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
热度：22

3
Visual features II[视觉功能II]
  Roland Memisevic(蒙特利尔大学) Visual features II
热度：33

4
On manifolds and autoencoders[关于歧管和自动编码器]
   Pascal Vincent(蒙特利尔大学) On manifolds and autoencoders
热度：23

5
Generative Models II[生成式模型II]
  Aaron Courville(蒙特利尔大学) Generative Models II
热度：30

6
Recurrent Neural Networks (RNNs)[递归神经网络（RNN）]
  Yoshua Bengio(蒙特利尔大学) Recurrent Neural Networks (RNNs)
热度：28

7
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：38

8
Recurrent Neural Networks[循环神经网络]
  Yoshua Bengio(蒙特利尔大学) This lecture will cover recurrent neural networks, the key ingredient in the deep learning toolbox for handling sequential computation and modelling s...
热度：43

9
Deep Learning:Theoretical Motivations[深度学习：理论动机]
  Yoshua Bengio(蒙特利尔大学) Deep Learning:Theoretical Motivations
热度：38

10
Why Does Unsupervised Pre-training Help Deep Discriminant Learning?[为什么无监督预训练有助于深层判别学习？]
  Dumitru Erhan(蒙特利尔大学) Recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with ...
热度：55
123>>> 1/3