@TomNotGeorge profile picture
Tom George @TomNotGeorge

Neuroscience/ML PhD @UCL. NeuroAI, navigation, hippocampus

Joined January 2022
  • Tweets 344
  • Following 382
  • Followers 846
66 Photos and videos
Pinned Tweet
Tom George@TomNotGeorge
13 Nov 2024
What are the brain’s “real” tuning curves? Our new preprint "SIMPL: Scalable and hassle-free optimisation of neural representations from behaviour” argues that existing techniques for latent variable discovery are lacking. We suggest a much simpl-er way to do things. 1/21🧵
5
50
287
39,596
Great work and a relevant read for neuroscientists and machine learners alike. Made me fundamentally reconsider how I thought about layer normalisation! Well done @RoyEyono
Roy Eyono@RoyEyono
Mar 19
How do neural circuits in the brain implement normalization? 🧠 In our new paper, we show that just normalizing sensory input isn't enough. Crucially, we must also normalize the error signals! 🧵👇 Paper: arxiv.org/abs/2603.17676
1
6
320
A little overdue but happy to announce that I 1) Got my PhD🎓 2) Started a postdoc and CNS Fellowship with Guillaume Lajoie and Blake Richards (@g_lajoie_ @tyrell_turing) Come find me at @Mila_Quebec in Montreal working on new things NeuroAI!
1
23
1,969
A great article from SWC on our neural data analysis technique (now accepted into ICLR). More updates to come soon...plus will be @CosyneMeeting presenting this too!
SWC@SWC_Neuro
13 Mar 2025
How does the brain represent imagined locations? Researchers at SWC, @GatsbyUCL and @UCL developed SIMPL, a method to refine neural tuning curves by correcting distortions from imagined locations—sharpening our view of place cell activity. Read more: sainsburywellcome.org/web/bl…
5
29
2,307
Application deadline has been extend. Two more weeks to apply...don't miss out!!
TReND-CaMinA@trend_camina
13 Jan 2025
Good news!🎉 The application deadline for TReND-CaMinA has been extended to ❗️31st January❗️ Don’t miss this chance to boost your computational neuroscience journey and become part of our community🧠✨ Apply now: trendinafrica.org/trend-cami… #Neuroscience #Education #ScienceForChange
1
2
1,037
🌍🧠💻Applications are well and truly open for the third CaMinA. African nationals studying biology, medicine, engineering, maths etc. can, and should, apply for this summer school in Zambia. Neuro and ML are changing the world and now I the time to get into them, please RT!
TReND-CaMinA@trend_camina
2 Jan 2025
🎉Happy New Year! Start 2025 by investing in your future!🚀 Just 2 weeks left to apply for our Computational Neuroscience & Machine Learning course🧠🤖 Let’s make this year one for growth & discovery. RT to spread the word!🙌 🔗trendinafrica.org/trend-cami… #Growth #Opportunity
5
13
1,022
CaMinA is back for its 3rd year...this time we're going to beautiful Zambia🇿🇲! I'm proud to see this course grow and bring together the smartest students across Africa with leading neuro institutes like @AllenInstitute and @SWC_Neuro Applications open soon, please share widely!
TReND-CaMinA@trend_camina
22 Nov 2024
🌍Exciting news! The 2025 TReND-CaMinA Course will be held in Lusaka, Zambia 🇿🇲 from July 7th–23rd. Dive into computational neuroscience and machine learning with us! 📅 Applications open: December 15th 🔗More info: trendinafrica.org/trend-cami… Stay tuned & spread the word! 🧠✨
4
20
1,593
Tom George retweeted
TReND-CaMinA@trend_camina
22 Nov 2024
🌍Exciting news! The 2025 TReND-CaMinA Course will be held in Lusaka, Zambia 🇿🇲 from July 7th–23rd. Dive into computational neuroscience and machine learning with us! 📅 Applications open: December 15th 🔗More info: trendinafrica.org/trend-cami… Stay tuned & spread the word! 🧠✨
33
48
8,751
What are the brain’s “real” tuning curves? Our new preprint "SIMPL: Scalable and hassle-free optimisation of neural representations from behaviour” argues that existing techniques for latent variable discovery are lacking. We suggest a much simpl-er way to do things. 1/21🧵
5
50
287
39,596
more replies
This isn’t cheating, behaviour has always been there for the taking and we should exploit it. If we ignore behaviour and initialise randomly SIMPL still works but the latent space isn’t smooth and “identifiable”. This is certainly something to consider…. 20/21
1
4
782
At the risk of rambling I'll end the thread here and perhaps do a deeper dive in the future. Give it a read (or better, try it on your data) and let us know your thoughts! tomge.org/papers/simpl/ 21/21

3
7
776
Load more