Curious.
Researching #MachineLearning for Scientific Discovery. #ml4science #ai4science
I choose #OpenSource and #OpenScience .
Solving problems in #LifeScience #Genomics #RadioAstronomy
| Website | https://ong-home.my |
| Location | Ngunnawal - Ngambri land, Australia |
| Pronouns | he/him |
So, I made a Thing. 📘
https://www.nowpublishers.com/article/Details/CIT-114
I'm very happy about (proud of) this Thing. If you have comments about the Thing, let me know! And if you want a copy of the Thing, please contact me (also, the draft is freely available online: https://ccanonne.github.io/survey-topics-dt.html).
Also, solutions to the exercises in the Thing coming soon (on the Thing's webpage), it just takes time to type with only two fingers.
Our paper visualization for @NeuripsConf '22 is back. It only shows this year's papers but I am working on the multi-year browser later this week. For now just some insights. ...
(1) Graph island:
New blog post on the NeurIPS'21 experiment re authors' perceptions of their own papers!
https://blog.ml.cmu.edu/2022/11/22/neurips2021-author-perception-experiment/
Key findings:
1) Authors significantly overestimate their papers' chances of acceptance. By like a LOT.
>
Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan(NeurIPS 2021 Program Chairs) Charvi Rastogi, Ivan Stelmakh, Zhenyu Xue, Hal Daumé III, Emma Pierson, and Nihar B. Shah There is a considerable body of research on peer review. Within the machine learning community, there
Is it time to rethink exploration in reinforcement learning to be about more than just finding the best policy for the immediate task at hand?
@balloch and I say yes: https://arxiv.org/abs/2210.06168
@rockt and Greffenstette say yes: https://arxiv.org/abs/2211.07819
The exploration--exploitation trade-off in reinforcement learning (RL) is a well-known and much-studied problem that balances greedy action selection with novel experience, and the study of exploration methods is usually only considered in the context of learning the optimal policy for a single learning task. However, in the context of online task transfer, where there is a change to the task during online operation, we hypothesize that exploration strategies that anticipate the need to adapt to future tasks can have a pronounced impact on the efficiency of transfer. As such, we re-examine the exploration--exploitation trade-off in the context of transfer learning. In this work, we review reinforcement learning exploration methods, define a taxonomy with which to organize them, analyze these methods' differences in the context of task transfer, and suggest avenues for future investigation.
Jura-Frage, gerne boosten:
Wenn ich in meiner Freizeit Software entwickle ohne auf Ressourcen meines Arbeitgebers zurückzugreifen und in einem arbeitsfernen Kontext, gibt es in Deutschland dann ein Gesetz, dass mir das geistige Eigentum an dieser Software sichert? Oder darf mein Arbeitgeber die Software beanspruchen? Eigentumsrechte a priori bei mir wäre Voraussetzung für Beteiligung an #OpenSource Projekten, richtig?
#FOSS #Software #dev #jura #recht #Copyright #legal #IntellectualProperty
Just read a big long thread from a former Twitter employee who not only defends the notion of relevancy algorithms but wants this built into Mastodon.
I'm tempted to write my own thread on why he's wrong. Should I?
Here's the original post: https://masto.ashfurrow.com/@jon@social.lot23.com/109372257459165739
I'm about to leave Mastodon for a few months. Not because I had a bad time, or couldn't find interesting people, or don't think the concept of a fediverse is dumb. On the contrary, I think it's great. I just have other stuff to do. But before I go, I want to share some thoughts as an ex-Twitter designer and someone who's been on Mastodon since 2018. #mastodon #twitter #ux #design #critique #hashtags #introduction 🧵
Cheng Soon Ong
Clément Canonne
Research Software Alliance
Hendrik Strobelt
Luc Rocher 🍃
Hal Daumé III
Mark Riedl
grob (teeth era) 🇺🇦🏳️🌈🏳️⚧️
NeurIPSConf
Chris Trottier