Master's thesis

  1. TAG: Task-based Accumulated Gradients for Lifelong learning
    by Pranshu Malviya, with Balaraman Ravindran and Sarath Chandar as supervisors.
    Indian Institute of Technology, Madras, January 2022.
    [thesis]

  2. PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
    by Mojtaba Faramarzi, with Sarath Chandar as supervisor.
    Université de Montréal, October 2021.
    [thesis]

  3. IIRC: Incremental Implicitly-Refined Classification
    by Mohamed Abdelsalam, with Sarath Chandar as supervisor.
    Université de Montréal, May 2021.
    [thesis]

  4. Continuous Coordination As a Realistic Scenario for Lifelong Learning
    by Akilesh Badrinaaraayanan, with Aaron Courville and Sarath Chandar as supervisors.
    Université de Montréal, April 2021.
    [thesis]