scispace - formally typeset
O

Olivier Delalleau

Researcher at Université de Montréal

Publications -  35
Citations -  6236

Olivier Delalleau is an academic researcher from Université de Montréal. The author has contributed to research in topics: Curse of dimensionality & Deep learning. The author has an hindex of 20, co-authored 34 publications receiving 5901 citations. Previous affiliations of Olivier Delalleau include Facebook & Centre de Recherches Mathématiques.

Papers
More filters
Posted Content

Theano: A Python framework for fast computation of mathematical expressions

Rami Al-Rfou, +111 more
TL;DR: The performance of Theano is compared against Torch7 and TensorFlow on several machine learning models and recently-introduced functionalities and improvements are discussed.
Proceedings Article

Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering

TL;DR: A unified framework for extending Local Linear Embedding, Isomap, Laplacian Eigenmaps, Multi-Dimensional Scaling as well as for Spectral Clustering is provided.
Journal ArticleDOI

Learning Eigenfunctions Links Spectral Embedding and Kernel PCA

TL;DR: A direct relation is shown between spectral embedding methods and kernel principal components analysis and how both are special cases of a more general learning problem: learning the principal eigenfunctions of an operator defined from a kernel and the unknown data-generating density.
Proceedings Article

Shallow vs. Deep Sum-Product Networks

TL;DR: It is proved there exist families of functions that can be represented much more efficiently with a deep network than with a shallow one, i.e. with substantially fewer hidden units.

Theano: Deep Learning on GPUs with Python

TL;DR: This paper presents Theano, a framework in the Python programming language for defining, optimizing and evaluating expressions involving high-level operations on tensors, and adds automatic symbolic differentiation, GPU support, and faster expression evaluation.