Learning a Deep Convolutional Network for Image Super-Resolution
Image Super-Resolution Using Deep Convolutional Networks Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang Department of Informaiton Engineering, The Chinese University of Hong Kong Microsoft Research Abstract We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represente
arXiv:1305.0445v2 [cs.LG] 7 Jun 2013
arXiv:1305.0445v2 [cs.LG] 7 Jun 2013 Deep Learning of Representations: Looking Forward Yoshua Bengio Department of Computer Science and Operations Research Université de Montréal, Canada Abstract. Deep learning research aims at discovering learning algorithms that discover mul- tiple levels of distributed representations, with higher levels representing more abstract con- cepts. Although the stu
Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling
Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling Haşim Sak, Andrew Senior, Françoise Beaufays Google, USA {hasim,andrewsenior,fsb@google.com} Abstract Long Short-Term Memory (LSTM) is a specific recurrent neu- ral network (RNN) architecture that was designed to model tem- poral sequences and their long-range dependencies more accu- rately than conve
A Neural Probabilistic Language Model
Journal of Machine Learning Research 3 (2003) 1137–1155 Submitted 4/02; Published 2/03 A Neural Probabilistic Language Model Yoshua Bengio BENGIOY@IRO.UMONTREAL.CA Réjean Ducharme DUCHARME@IRO.UMONTREAL.CA Pascal Vincent VINCENTP@IRO.UMONTREAL.CA Christian Jauvin JAUVINC@IRO.UMONTREAL.CA Département d’Informatique et Recherche Opérationnelle Centre de Recherche Mathématiques Université de Montréal
DRAW: A Recurrent Neural Network For Image Generation
This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for gener
Investigation of Ensemble Models For Sequence Learning - Microsoft Research
While ensemble models have proven useful for sequence learning tasks there is relatively fewer work that provide insights into what makes them powerful. In this paper, we investigate the empirical behavior of the ensemble approaches on sequence modeling, specifically for the semantic tagging task. We explore this by comparing the performance of commonly used and easy to implement ensemble methods
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covar
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to auto
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Non-negative Principal Component Analysis: Message Passing Algorithms and Sharp Asymptotics
Nonnegative Sparse PCA
Understanding the difficulty of training deep feedforward neural networks
http://research.google.com/people/jeff/CIKM-keynote-Nov2014.pdf
http://arxiv.org/pdf/1409.0473v4
http://nal.co/papers/KalchbrennerBlunsom_EMNLP13
http://research.google.com/pubs/archive/38131.pdf
Photo Tourism: Microsoft Research, Interactive Visual Media Group
LSTM can Solve Hard Long Time Lag Problems
https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.248.4448&rep=rep1&type=pdf
http://arxiv.org/pdf/1502.03520v1
Gated Feedback Recurrent Neural Networks