Summaries imported from https://twitter.com/hugo_larochelle/timelines/639067398511968256

Using Fast Weights to Attend to the Recent Past

arXiv e-Print archive - 2016 via arXiv

Keywords: stat.ML, cs.LG, cs.NE

more

arXiv e-Print archive - 2016 via arXiv

Keywords: stat.ML, cs.LG, cs.NE

Stochastic Backpropagation through Mixture Density Distributions

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.NE

more

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.NE

Learning End-to-end Video Classification with Rank-Pooling

International Conference on Machine Learning - 2016 via Bibsonomy

Keywords: dblp

International Conference on Machine Learning - 2016 via Bibsonomy

Keywords: dblp

Learning Representations for Counterfactual Inference

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

Swapout: Learning an ensemble of deep architectures

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.CV, cs.LG, cs.NE

more

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.CV, cs.LG, cs.NE

One-shot Learning with Memory-Augmented Neural Networks

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.LG

more

arXiv e-Print archive - 2016 via arXiv

Keywords: cs.LG

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

Training recurrent networks online without backtracking

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Accelerating Stochastic Gradient Descent via Online Learning to Sample

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Semi-supervised Learning with Ladder Networks

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Variational Dropout and the Local Reparameterization Trick

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Teaching Machines to Read and Comprehend

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Bayesian dark knowledge

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2015 via Bibsonomy

Keywords: dblp

Learning to See by Moving

International Conference on Computer Vision - 2015 via Bibsonomy

Keywords: dblp

International Conference on Computer Vision - 2015 via Bibsonomy

Keywords: dblp

Clustering is Efficient for Approximate Maximum Inner Product Search

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Gradient-based Hyperparameter Optimization through Reversible Learning

International Conference on Machine Learning - 2015 via Bibsonomy

Keywords: dblp

International Conference on Machine Learning - 2015 via Bibsonomy

Keywords: dblp

Net2Net: Accelerating Learning via Knowledge Transfer

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Sequence Level Training with Recurrent Neural Networks

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

MuProp: Unbiased Backpropagation for Stochastic Neural Networks

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

A note on the evaluation of generative models

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Bibsonomy

Keywords: dblp

Variational inference for Monte Carlo objectives

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

Ensemble Robustness of Deep Learning Algorithms

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

Latent Predictor Networks for Code Generation

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

Adaptive Computation Time for Recurrent Neural Networks

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Bibsonomy

Keywords: dblp

About