Paper Review: Superposition of many models into one

For this Friday’s journal club, we will be looking at a recently published paper by Bruno Olshausen at the Redwood Institute. It is about a more plausible algorithm in terms of biological constraints. It also ties well with the latest discussions on Continuous Learning, it provides an ingenious and elegant approach to the catastrophic forgetting problem in multitask learning.

Here is the link to the paper:


Just a reminder that this live streamed journal club meeting will start in about 45 minutes.

1 Like