I
Irina Rish
Researcher at Université de Montréal
Publications - 221
Citations - 7792
Irina Rish is an academic researcher from Université de Montréal. The author has contributed to research in topics: Computer science & Approximation algorithm. The author has an hindex of 34, co-authored 198 publications receiving 6830 citations. Previous affiliations of Irina Rish include IBM & University of California, Irvine.
Papers
More filters
Journal ArticleDOI
Knowledge Distillation for Federated Learning: a Practical Guide
TL;DR: In this paper , the authors provide a review of KD-based algorithms tailored for specific FL issues, such as model drifts, model updates, and parameter-averaging aggregation in presence of non-IID data distributions.
Posted Content
Sequoia: A Software Framework to Unify Continual Learning Research
Fabrice Normandin,Florian Golemo,Oleksiy Ostapenko,Pau Rodriguez,Matthew Riemer,Julio Hurtado,Khimya Khetarpal,Dominic Zhao,Ryan Lindeborg,Timothée Lesort,Laurent Charlin,Irina Rish,Massimo Caccia +12 more
TL;DR: Sequoia as mentioned in this paper is a publicly available software framework for Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains, which includes a growing suite of methods which are easy to extend and customize.
Patent
Method and apparatus for authoring and optimizing flowcharts
TL;DR: In this article, a dependency matrix of questions and answers related by state or underlying problem cause is generated, and a corresponding flowchart is then calculated based on the information in the dependency matrix, and also the likelihood of the various problems and their causes.
Journal ArticleDOI
Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks.
German Abrevaya,Guillaume Dumas,Aleksandr Y. Aravkin,Peng Zheng,Jean-Christophe Gagnon-Audet,James R. Kozloski,Pablo Polosecki,Guillaume Lajoie,David D. Cox,Silvina Ponce Dawson,Guillermo A. Cecchi,Irina Rish +11 more
TL;DR: This work develops a novel and efficient approach to the nontrivial problem of parameters estimation for a network of coupled dynamical systems from multivariate data and demonstrates that the resulting VDP models are both accurate and interpretable, as VDP's coupling matrix reveals anatomically meaningful excitatory and inhibitory interactions across different brain subsystems.