Very excited to have posted a new preprint on my PhD work in the @brody_lab where we show that rats can achieve near-optimal time investment in a confidence-guided waiting task https://t.co/ogMkGIMN6w.
Check out our #ICLR2023#physics4ml workshop paper with poster tomorrow.
The RL Perceptron: A solvable model of high-D policy learning and generalisation with lots of follow up potential!
Great fun with @nishpathead, @sebalexlee, @stefesseM and @sebastiangoldt
Excited to share our paper at #ICLR2023 titled: On the Specialization of Neural Modules.
Led by @devonjarvi5 with @kleinric and @BenjaminRosman
Paper: https://t.co/ltxVSJALUT
Poster #115, Wed 16:30: https://t.co/1xuq1WtPbq
(1/10)
I had a lot of fun presenting our poster this morning!
Thank you to everybody that came 😊
If you missed it make sure you check out our paper 📝: https://t.co/HY0k2r3c2S
Excited to share our new paper at #NeurIPS2022!
Prior knowledge deeply impacts learning dynamics. We derive exact solutions in deep linear networks for a rich class of initialisations.
Paper: https://t.co/JkHBjzIR6v
Poster: Nov 29 11-1 Hall J #511
A 🧵…
So excited and happy that this is finally out: A big chunk of my PhD with loads of fun results! If you happen to be at #NeurIPS2022 make sure to come to Hall J - Poster #511 on Tuesday, where @ClementineDomi6 will present our work!
Excited to share our new paper at #NeurIPS2022!
Prior knowledge deeply impacts learning dynamics. We derive exact solutions in deep linear networks for a rich class of initialisations.
Paper: https://t.co/JkHBjzIR6v
Poster: Nov 29 11-1 Hall J #511
A 🧵…
So Meta AI (aka Facebook research) came up with a large language model for science: https://t.co/yEP069BVda. And I came up with a game: Ask it for the theorem that you have proved! Anyone out there who can explain my theorem to me? Does it even make sense?
Come and join us!
If you have questions about what we do, how we do it, how it is to live in the UK ... and how it is to work with Andrew (spoiler: he is a 5 out of 5 stars advisor) feel free to drop me a line
Job alert! Postdoc in deep learning theory @GatsbyUCL
We're currently interested in theories of systematic generalization, architecture, and learning dynamics.
Apply by Aug 25:
https://t.co/avA3yASJI2
“The Neural Race Reduction: Dynamics of abstraction in gated networks”
New paper @icmlconf
We derive reductions and occasionally exact explicit solutions for the learning dynamics of a class of nonlinear deep networks in the rich representation learning regime.
Is there any better environment to present work on gradient-based optimisation than this? I don't think so!
I am feeling very happy and privileged to be part of the #Leshouches2022 summer school on statistical physics & machine learning :)
German for beginners: "Und wenn ich mal nicht weiter weiß, gründ' ich einen Arbeitskreis" - "If you are stuck and don't know what to do, establish a new committee". Example: Germany's chancellor Scholz suggesting a "climate club" at G7 summit to lower greenhouse gas emissions
Exam question: Discuss the difference between innate and learned behaviour and the resulting implications for modern AI given the following bird behaviour (using 280 characters, i.e., 1x tweet)
Saxelab is hiring it’s first *experimental* postdoc or research scientist!
We aim to understand how representations change in multi-layered neural systems, to test links between modern deep learning and biological learning.
We’re at #cosyne22 or always happy to chat! 👇
Tweeps, I am hiring (big time) - please spread the word.
I am looking for three postdocs in the space of neuro-inspired ML and cognitive computational neuroscience to join us at the Institute of Cognitive Science (@UniOsnabrueck).
Here is why this is a great opportunity: 🧵
The result of environmentally harmful subsidies and taxes: Flight 5€ vs Train 176€. I am privileged/enduring enough to take the train but I know that many are not. Let's start taxing kerosene/airlines properly such that prices create an incentive to make the right choice - now!