Search Results - "de Brebisson, Alexandre"
-
1
Deep neural networks for anatomical brain segmentation
Published in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2015)“…We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a…”
Get full text
Conference Proceeding Journal Article -
2
Deep Neural Networks for Anatomical Brain Segmentation
Published 09-02-2015“…We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a…”
Get full text
Journal Article -
3
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
Published 08-10-2019“…Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we…”
Get full text
Journal Article -
4
ObamaNet: Photo-realistic lip-sync from text
Published 06-12-2017“…We present ObamaNet, the first architecture that generates both audio and synchronized photo-realistic lip-sync videos from any new text. Contrary to other…”
Get full text
Journal Article -
5
A Deep Reinforcement Learning Chatbot (Short Version)
Published 20-01-2018“…We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize…”
Get full text
Journal Article -
6
A Deep Reinforcement Learning Chatbot
Published 07-09-2017“…We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize…”
Get full text
Journal Article -
7
A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations
Published 19-09-2016“…The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from…”
Get full text
Journal Article -
8
The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family
Published 29-04-2016“…Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations…”
Get full text
Journal Article -
9
An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family
Published 16-11-2015“…In a multi-class classification problem, it is standard to model the output of a neural network as a categorical distribution conditioned on the inputs. The…”
Get full text
Journal Article -
10
Exact gradient updates in time independent of output size for the spherical loss family
Published 26-06-2016“…An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g…”
Get full text
Journal Article -
11
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
Published 22-12-2014“…An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g…”
Get full text
Journal Article -
12
Artificial Neural Networks Applied to Taxi Destination Prediction
Published 31-07-2015“…We describe our first-place solution to the ECML/PKDD discovery challenge on taxi destination prediction. The task consisted in predicting the destination of a…”
Get full text
Journal Article -
13
Theano: A Python framework for fast computation of mathematical expressions
Published 09-05-2016“…Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its…”
Get full text
Journal Article