I am one of the founders of lyrebird.ai, a startup backed by Andreessen Horowitz, RedPoint Ventures and YCombinator (S17).

I am also a fourth-year PhD student at the MILA lab in Montréal under the joint supervision of Professors Pascal Vincent and Yoshua Bengio (my interest in neural nets started back in 2008 when I coded LeNet-5 in Maple (!)).

Before my PhD, I studied at Imperial College under the supervisions of Professors Murray Shanahan, Giovanni Montana and Mauricio Barahona.

Contacts: email, github, linkedin.


A Cheap Linear Attention Mechanism with Fast Lookups and Fixed-Size Representations,
Alexandre de Brébisson and Pascal Vincent,
2016 ArXiv.

The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family,
Alexandre de Brébisson and Pascal Vincent,
2016 ArXiv.

An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family,
Alexandre de Brébisson and Pascal Vincent,
2016 ICLR.

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets,
Pascal Vincent, Alexandre de Brébisson, Xavier Bouthillier,
2015 NIPS, oral presentation.

Artificial Neural Networks Applied to Taxi Destination Prediction,
Alexandre de Brébisson, Étienne Simon, Alex Auvolat, Pascal Vincent, Yoshua Bengio,
2015 ECML/PKDD, first-place of the discovery challenge out of 381 teams.

Deep Neural Networks for Anatomical Brain Segmentation,
Alexandre de Brebisson, Giovanni Montana,
2015 CVPR Bioimage, best paper award.