Alexandre de Brébisson

is this you? claim profile

∙ 0 followers
Université de Montréal

Founder of Lyrebird.ai and PhD student at Montreal Institute for Learning Algorithms

Featured Co-authors

Yoshua Bengio
334 publications
Kyunghyun Cho
157 publications
Aaron Courville
112 publications
Joelle Pineau
89 publications
Razvan Pascanu
56 publications
Ian Goodfellow
50 publications
Ying Zhang
45 publications
Pascal Vincent
42 publications
Giovanni Montana
38 publications
Orhan Firat
35 publications
Christopher Pal
35 publications

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

Previous works <cit.> have found that generating coherent raw audio wave...
10/08/2019 ∙ by Kundan Kumar, et al. ∙ 0 ∙ share

read it
A Deep Reinforcement Learning Chatbot (Short Version)

We present MILABOT: a deep reinforcement learning chatbot developed by t...
01/20/2018 ∙ by Iulian V. Serban, et al. ∙ 0 ∙ share

read it
A Deep Reinforcement Learning Chatbot

We present MILABOT: a deep reinforcement learning chatbot developed by t...
09/07/2017 ∙ by Iulian V. Serban, et al. ∙ 0 ∙ share

read it
A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations

The softmax content-based attention mechanism has proven to be very bene...
09/19/2016 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ share

read 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 ∙ share

read 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 ∙ share

read it
The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family

Despite being the standard loss function to train multi-class neural net...
04/29/2016 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ share

read it
An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family

In a multi-class classification problem, it is standard to model the out...
11/16/2015 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ share

read it
Artificial Neural Networks Applied to Taxi Destination Prediction

We describe our first-place solution to the ECML/PKDD discovery challeng...
07/31/2015 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ share

read it
Deep Neural Networks for Anatomical Brain Segmentation

We present a novel approach to automatically segment magnetic resonance ...
02/09/2015 ∙ by Alexandre de Brébisson, et al. ∙ 0 ∙ share

read 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 ∙ share

read it