Portrait de Sarath Chandar

Sarath Chandar

Membre académique principal

sarath.chandar@mila.quebec

Chaire en IA Canada-CIFAR

Professeur associé, Polytechnique Montréal, Département d'informatique et de génie logiciel

Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle

Indian Institute of Technology Madras

Sujets de recherche

Alignement de l'IA

Apprentissage automatique médical

Apprentissage de représentations

Apprentissage en ligne

Apprentissage par renforcement

Apprentissage par transfert

Apprentissage profond

Apprentissage tout au long de la vie

Grands modèles de langage (LLM)

IA digne de confiance

Interprétabilité

Modèles de fondation

Optimisation

Réseaux de neurones récurrents

Systèmes multi-agents

Traitement du langage naturel

XAI (IA explicable)

Biographie

Sarath Chandar est professeur associé au départment de génie informatique et génie logiciel de Polytechnique Montréal, où il dirige le laboratoire de recherche Chandar. Il est également membre académique principal à Mila – Institut québécois d’intelligence artificielle, et titulaire d'une chaire en IA Canada-CIFAR et d'une Chaire de recherche du Canada en apprentissage machine permanent.

Ses recherches portent sur l'apprentissage tout au long de la vie, l'apprentissage profond, l'optimisation, l'apprentissage par renforcement et le traitement du langage naturel. Pour promouvoir la recherche sur l'apprentissage tout au long de la vie, Sarath Chandar a créé la Conférence sur les agents d'apprentissage tout au long de la vie (CoLLAs) en 2022 et a présidé le programme en 2022 et en 2023. Il est titulaire d'un doctorat de l'Université de Montréal et d'une maîtrise en recherche de l'Indian Institute of Technology Madras.

Étudiants actuels

Maîtrise recherche - UdeM

Davide Baldelli

Doctorat - Polytechnique

Co-superviseur⋅e :

Antoine Clavaud

Maîtrise recherche - Polytechnique

Doctorat - Polytechnique

Superviseur⋅e principal⋅e :

Naga Karthik Enamundram

Doctorat - Polytechnique

Superviseur⋅e principal⋅e :

Julien Cohen-Adad

emvnagakarthik@gmail.com

Prashant Govindarajan

Doctorat - Polytechnique

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche - UdeM

Superviseur⋅e principal⋅e :

Maryam Hashemzadeh

Doctorat - UdeM

David Heurtel--Depeiges

Doctorat - Polytechnique

Doctorat - UdeM

Amir Ardalan Kalantari Dehaghi

Collaborateur·rice alumni

Maîtrise recherche - Polytechnique

Ekaterina Lobacheva

Postdoctorat - UdeM

Doctorat - Polytechnique

Co-superviseur⋅e :

andreas.madsen@mila.quebec

Pranshu Malviya

Doctorat - Polytechnique

Maîtrise recherche - Polytechnique

Mohamed Amine Merzouk

Postdoctorat - Polytechnique

Superviseur⋅e principal⋅e :

Hadi NekoeiQachkanloo

Doctorat - UdeM

Doctorat - UdeM

Doctorat - UdeM

Janarthanan Rajendran

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Mathieu Reymond

Postdoctorat

Francois Rivest

Visiteur de recherche indépendant

Mohammad R. Samsami

Maîtrise recherche - UdeM

Maîtrise recherche - UdeM

Arjun Vaithilingam Sudhakar

Doctorat - Polytechnique

Abdelrahman Zayed

Doctorat - Polytechnique

Doctorat - Polytechnique

Doctorat - Polytechnique

Billets de blogue

A digital picture of Bert from Sesame street, wering black trench coat and sunglasses

3 mars 2025

NeoBERT: une nouvelle frontière pour les modèles de langage encodeurs open-source

par

Quentin Fournier

1 octobre 2024

Comment expliquer l’IA et s’assurer que cette explication est vraie? Les modèles mesurables de fidélité vous indiquent comment y parvenir

par

Siva Reddy

Publications

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study

Chinnadhurai Sankar

Sandeep Subramanian

Neural generative models have been become increasingly popular when building conversational agents. They offer flexibility, can be easily ad… (voir plus)apted to new domains, and require minimal domain engineering. A common criticism of these systems is that they seldom understand or use the available dialog history effectively. In this paper, we take an empirical approach to understanding how these models use the available dialog history by studying the sensitivity of the models to artificially introduced unnatural changes or perturbations to their context at test time. We experiment with 10 different types of perturbations on 4 multi-turn dialog datasets and find that commonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most perturbations such as missing or reordering utterances, shuffling words, etc. Also, by open-sourcing our code, we believe that it will serve as a useful diagnostic tool for evaluating dialog systems in the future.

2019-07-01

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (publié)

Environments for Lifelong Reinforcement Learning

Khimya Khetarpal

Shagun Sodhani

To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific ta… (voir plus)sk but also to constantly build more complex skills and scaffold their knowledge about the world, without forgetting what has already been learned. In this paper, we discuss the desired characteristics of environments that can support the training and evaluation of lifelong reinforcement learning agents, review existing environments from this perspective, and propose recommendations for devising suitable environments in the future.

2018-11-26

ArXiv (prépublication)

On Training Recurrent Neural Networks for Lifelong Learning

Shagun Sodhani

Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we stud… (voir plus)y these challenges in the context of sequential supervised learning with emphasis on recurrent neural networks. To evaluate the models in the lifelong learning setting, we propose a curriculum-based, simple, and intuitive benchmark where the models are trained on tasks with increasing levels of difficulty. To measure the impact of catastrophic forgetting, the model is tested on all the previous tasks as it completes any task. As a step towards developing true lifelong learning systems, we unify Gradient Episodic Memory (a catastrophic forgetting alleviation approach) and Net2Net(a capacity expansion approach). Both these models are proposed in the context of feedforward networks and we evaluate the feasibility of using them for recurrent networks. Evaluation on the proposed benchmark shows that the unified model is more suitable than the constituent models for lifelong learning setting.

2018-11-16

ArXiv (prépublication)