Efficient Continual Learning with Modular Networks and Task-Driven Priors

2 code implementations • ICLR 2021 • Tom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato

Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task.

Continual Learning

Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks

1 code implementation • CVPR 2018 • Tom Veniat, Ludovic Denoyer

We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost.