Skip to content

2013.md

Latest commit

 

History

History
44 lines (38 loc) · 9.7 KB

2013.md

File metadata and controls

44 lines (38 loc) · 9.7 KB

2013

Deep Learning

  • Adaptive dropout for training deep neural networks. [[pdf]](docs/2013/Adaptive dropout for training deep neural networks.pdf) [url]
  • [VAE] Auto-Encoding Variational Bayes. [arxiv] [talk] ⭐
  • Better Mixing via Deep Representations. [[pdf]](docs/2013/Yoshua Bengio.Better Mixing via Deep Representations.pdf) [url]
  • Deep Fisher Networks for Large-Scale Image Classification. [[pdf]](docs/2013/Deep Fisher Networks for Large-Scale Image Classification.pdf) [url]
  • Deep Learning of Representations-looking forward. [url]]
  • Deep Neural Networks for Object Detection. [[pdf]](docs/2013/Deep Neural Networks for Object Detection.pdf) [url] ⭐
  • Dropout Training as Adaptive Regularization. [[pdf]](docs/2013/Dropout Training as Adaptive Regularization.pdf) [url]
  • Efficient Estimation of Word Representations in Vector Space. [url] ⭐
  • Exploiting Similarities among Languages for Machine Translation. [url]
  • Generalized Denoising Auto-Encoders as Generative Models. [[pdf]](docs/2013/Generalized Denoising Auto-Encoders as Generative Models.pdf) [url] [code]
  • Generating Sequences With Recurrent Neural Networks. [arxiv] ⭐
  • Generative Stochastic Networks Trainable by Backprop. [arxiv] [code]
  • Learning a Deep Compact Image Representation for Visual Tracking. [[pdf]](docs/2013/Learning a Deep Compact Image Representation for Visual Tracking.pdf) [url]
  • Learning Hierarchical Features for Scene Labeling. [[pdf]](docs/2013/Learning Hierarchical Features for Scene Labeling.pdf) [url] ⭐
  • Learning Multi-level Sparse Representations. [[pdf]](docs/2013/Learning Multi-level Sparse Representations.pdf) [url]
  • [Maxout] Maxout Networks. [[pdf]](docs/2013/Maxout Networks.pdf) [url] ⭐
  • No More Pesky Learning Rates. [[pdf]](docs/2013/No More Pesky Learning Rates.pdf) [url]
  • On autoencoder scoring. [[pdf]](docs/2013/On autoencoder scoring.pdf) [url]
  • On the difficulty of training recurrent neural networks. [[pdf]](docs/2013/On the difficulty of training recurrent neural networks(2013).pdf) [url]
  • On the importance of initialization and momentum in deep learning.[[pdf]](docs/2013/On the importance of initialization and momentum in deep learning.pdf) [url]
  • Regularization of Neural Networks using DropConnect. [[pdf]](docs/2013/Regularization of Neural Networks using DropConnect.pdf) [url]
  • Representation Learning A Review and New Perspectives. [[pdf]](docs/2013/Representation Learning A Review and New Perspectives.pdf) [url] ⭐
  • [RCNN] Rich feature hierarchies for accurate object detection and semantic segmentation. [arxiv] [code]:star:
  • Scaling up Spike-and-Slab Models for Unsupervised Feature Learning. [[pdf]](docs/2013/Scaling up Spike-and-Slab Models for Unsupervised Feature Learning.pdf) [url]
  • Speech Recognition with Deep Recurrent Neural Networks. [url] ⭐
  • Stochastic Pooling for Regularization of Deep Convolutional Neural Networks. [[pdf]](docs/2013/Stochastic Pooling for Regularization of Deep Convolutional Neural Networks.pdf) [url]
  • [ZFNet] Visualizing and Understanding Convolutional Networks. [[pdf]](docs/2013/Visualizing and Understanding Convolutional Networks.pdf) [url] ⭐

Transfer learning

  • Active transfer learning for cross-system recommendation. [pdf]
  • Combating Negative Transfer From Predictive Distribution Differences. [url]
  • Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification. [pdf] ⭐
  • On handling negative transfer and imbalanced distributions in multiple source transfer learning. [pdf]
  • Transfer feature learning with joint distribution adaptation. [pdf]

Deep Reinforcement Learning

  • Evolving large-scale neural networks for vision-based reinforcement learning. [idsia] ⭐
  • Playing Atari with Deep Reinforcement Learning. [toronto] ⭐