1 code implementation • 13 Dec 2021 • Matthew Riemer, Sharath Chandra Raparthy, Ignacio Cases, Gopeshh Subbaraj, Maximilian Puelma Touzel, Irina Rish
The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios.
1 code implementation • 6 Feb 2021 • Meriem Bensouda Koraichi, Maximilian Puelma Touzel, Andrea Mazzolini, Thierry Mora, Aleksandra M. Walczak
High-throughput sequencing of T- and B-cell receptors makes it possible to track immune repertoires across time, in different tissues, in acute and chronic diseases and in healthy individuals.
no code implementations • 25 Jun 2020 • Ryan Vogt, Maximilian Puelma Touzel, Eli Shlizerman, Guillaume Lajoie
Recurrent neural networks (RNNs) have been successfully applied to a variety of problems involving sequential data, but their optimization is sensitive to parameter initialization, architecture, and optimizer hyperparameters.
1 code implementation • 17 Dec 2019 • Maximilian Puelma Touzel, Aleksandra M. Walczak, Thierry Mora
High-throughput sequencing of B- and T-cell receptors makes it possible to track immune repertoires across time, in different tissues, and in acute and chronic diseases or in healthy individuals.
Quantitative Methods
1 code implementation • NeurIPS 2019 • Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie
A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary.