Anna Koop

I'm in your talk, live-tooting it. Don't let the activity fool you, I'm listening.

Reinforcement Learning researcher, general enthusiast. Finishing PhD after exploring many alternate time streams.

2022-11-25

I'm looking for references for #DeepLearning, #ContinualDeepLearning, on very long timescales, specifically #LossOfPlasticity as in Rich/Shibhansh's talk here: youtube.com/watch?v=p_zknyfV9f Anyone have any?

2022-11-16

@kongaloosh.com

Hey fellow dual-account person. But you've explicitly noted you're not using the one here.

2022-11-16

@annakoop@octodon.social

But I will say it's much handier finding fellow researchers when you're sitting on the same instance as them. #MastodonSetup

2022-11-16

Getting distracted with mastodon setup, so I went and made a dual account. Here for all-science, @annakoop@octodon.social for science and general mayhem.

Will I regret this? PROBABLY! Will I experiment anyway? ALWAYS.

DAGs are too easy, cycles are where it's at.

2022-11-16

@glialfire I'm trying the dual-account thing myself for now. We'll see how it goes!

2022-11-16

@cmaclell I think that's an important point. I like framing it as #transfer learning, because you have a network that has settled pretty solidly into a particular basin of the parameter space, based on the data it was trained with. This is VERY different than a system that has abstracted generalizable, relevant concepts, which is what I think people want to be true in #zeroshot learning.

2022-11-16

@thegradient Maaaaybe but then how do you decide which ones? Vote on it? How narrow is the scope?

Some will happen naturally with following.

2022-11-16

@Techronic9876 If I understand correctly, the federated feed is still limited to the union of my instance's follows (see here: sigmoid.social/@thegradient/10)

Maybe there could be an instance with an account that just follows all known accounts? Then your account on that instance would have twitter-equivalent federated timeline.

Ugh, let's not do that on @sigmoid.social though.

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst