Gated Linear Networks (DeepMind Paper)

Papers
#1

I presume this paper is relevant to continual learning since they speak about being able to avoid catastrophic forgetting.
https://arxiv.org/abs/1910.01526

I’ll read it and see if I can use the ideas with any of the specialized algorithms I have.
Maybe you know about the paper since the first version was from last year.

#2

I read the paper few months ago and I agree with you that the main idea behind it is very interesting. I was planning to dig deeper into the model and I hope to be able to do it soon.

Keep us updated if you integrate GLN in some of your works, I’d be glad to give it a read :slight_smile:

1 Like