
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measuremen...
11/21/2018 ∙ by Jure Žbontar, et al. ∙ 20 ∙ shareread it

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
Generative adversarial networks have been very successful in generative ...
06/11/2019 ∙ by Hugo Berard, et al. ∙ 1 ∙ shareread it

An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
Batch normalization has been widely used to improve optimization in deep...
07/31/2019 ∙ by Vincent Michalski, et al. ∙ 1 ∙ shareread it

Recombinator Networks: Learning CoarsetoFine Feature Aggregation
Deep neural networks with alternating convolutional, maxpooling and dec...
11/23/2015 ∙ by Sina Honari, et al. ∙ 0 ∙ shareread it

Representation Learning: A Review and New Perspectives
The success of machine learning algorithms generally depends on data rep...
06/24/2012 ∙ by Yoshua Bengio, et al. ∙ 0 ∙ shareread it

Highdimensional sequence transduction
We investigate the problem of transforming an input sequence into a high...
12/09/2012 ∙ by Nicolas BoulangerLewandowski, et al. ∙ 0 ∙ shareread it

Generalized Denoising AutoEncoders as Generative Models
Recent work has shown how denoising and contractive autoencoders implici...
05/29/2013 ∙ by Yoshua Bengio, et al. ∙ 0 ∙ shareread it

Convergent TreeBackup and Retrace with Function Approximation
Offpolicy learning is key to scaling up reinforcement learning as it al...
05/25/2017 ∙ by Ahmed Touati, et al. ∙ 0 ∙ shareread it

GSNs : Generative Stochastic Networks
We introduce a novel training principle for probabilistic models that is...
03/18/2015 ∙ by Guillaume Alain, et al. ∙ 0 ∙ shareread it

Exact gradient updates in time independent of output size for the spherical loss family
An important class of problems involves training deep neural networks wi...
06/26/2016 ∙ by Pascal Vincent, et al. ∙ 0 ∙ shareread it

Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
Generative modeling of high dimensional data like images is a notoriousl...
08/08/2017 ∙ by Gabriel Huang, et al. ∙ 0 ∙ shareread it

Improving Landmark Localization with SemiSupervised Learning
We present two techniques to improve landmark localization from partiall...
09/05/2017 ∙ by Sina Honari, et al. ∙ 0 ∙ shareread it

Artificial Neural Networks Applied to Taxi Destination Prediction
We describe our firstplace solution to the ECML/PKDD discovery challeng...
07/31/2015 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ shareread it

Learning to Generate Samples from Noise through Infusion Training
In this work, we investigate a novel training procedure to learn a gener...
03/20/2017 ∙ by Florian Bordes, et al. ∙ 0 ∙ shareread it

A Cheap Linear Attention Mechanism with Fast Lookups and FixedSize Representations
The softmax contentbased attention mechanism has proven to be very bene...
09/19/2016 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ shareread it

The Zloss: a shift and scale invariant classification loss belonging to the Spherical Family
Despite being the standard loss function to train multiclass neural net...
04/29/2016 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ shareread it

An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family
In a multiclass classification problem, it is standard to model the out...
11/16/2015 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ shareread it

Dropout as data augmentation
Dropout is typically interpreted as bagging a large number of models sha...
06/29/2015 ∙ by Xavier Bouthillier, et al. ∙ 0 ∙ shareread it

Learning invariant features through local space contraction
We present in this paper a novel approach for training deterministic aut...
04/21/2011 ∙ by Salah Rifai, et al. ∙ 0 ∙ shareread it

Adding noise to the input of a model trained with a regularized objective
Regularization is a well studied problem in the context of neural networ...
04/16/2011 ∙ by Salah Rifai, et al. ∙ 0 ∙ shareread it

EmoNets: Multimodal deep learning approaches for emotion recognition in video
The task of the emotion recognition in the wild (EmotiW) Challenge is to...
03/05/2015 ∙ by Samira Ebrahimi Kahou, et al. ∙ 0 ∙ shareread it

Modeling Temporal Dependencies in HighDimensional Sequences: Application to Polyphonic Music Generation and Transcription
We investigate the problem of modeling symbolic sequences of polyphonic ...
06/27/2012 ∙ by Nicolas BoulangerLewandowski, et al. ∙ 0 ∙ shareread it

A Generative Process for Sampling Contractive AutoEncoders
The contractive autoencoder learns a representation of the input data t...
06/27/2012 ∙ by Salah Rifai, et al. ∙ 0 ∙ shareread it

Learning to Compute Word Embeddings On the Fly
Words in natural language follow a Zipfian distribution whereby some wor...
06/01/2017 ∙ by Dzmitry Bahdanau, et al. ∙ 0 ∙ shareread it

Hierarchical Memory Networks
Memory networks are neural networks with an explicit memory component th...
05/24/2016 ∙ by Sarath Chandar, et al. ∙ 0 ∙ shareread it

Clustering is Efficient for Approximate Maximum Inner Product Search
Efficient Maximum Inner Product Search (MIPS) is an important task that ...
07/21/2015 ∙ by Alex Auvolat, et al. ∙ 0 ∙ shareread it

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
An important class of problems involves training deep neural networks wi...
12/22/2014 ∙ by Pascal Vincent, et al. ∙ 0 ∙ shareread it

A Variational Inequality Perspective on Generative Adversarial Nets
Stability has been a recurrent issue in training generative adversarial ...
02/28/2018 ∙ by Gauthier Gidel, et al. ∙ 0 ∙ shareread it

Randomized Value Functions via Multiplicative Normalizing Flows
Randomized value functions offer a promising approach towards the challe...
06/06/2018 ∙ by Ahmed Touati, et al. ∙ 0 ∙ shareread it

Fast Approximate Natural Gradient Descent in a Kroneckerfactored Eigenbasis
Optimization algorithms that leverage gradient covariance information, s...
06/11/2018 ∙ by Thomas George, et al. ∙ 0 ∙ shareread it

Theano: A Python framework for fast computation of mathematical expressions
Theano is a Python library that allows to define, optimize, and evaluate...
05/09/2016 ∙ by The Theano Development Team, et al. ∙ 0 ∙ shareread it

Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
The goal of MRI reconstruction is to restore a high fidelity image from ...
02/08/2019 ∙ by Zizhao Zhang, et al. ∙ 0 ∙ shareread it

SVRG for Policy Evaluation with Fewer Gradient Evaluations
Stochastic variancereduced gradient (SVRG) is an optimization method or...
06/09/2019 ∙ by Zilun Peng, et al. ∙ 0 ∙ shareread it

Stochastic Neural Network with Kronecker Flow
Recent advances in variational inference enable the modelling of highly ...
06/10/2019 ∙ by ChinWei Huang, et al. ∙ 0 ∙ shareread it
Pascal Vincent
is this you? claim profile
Associate Professor Montreal Institute for Learning Algorithms (MILA) Department of Computer Science and Operational Research University of Montreal, Research Scientist at Facebook A.I. Research