Agostina Palmigiano

@apalmigiano.bsky.social

Lecturer at @GatsbyUCL palmigianolab.com

Submission deadline extended! Submit your poster or lightning talk abstract by Wednesday 15th October 2025, 12:00pm

UCL NeuroAI@ucl-neuroai.bsky.social · 12mo ago

📢 We are very happy to announce the 2025 @ucl.ac.uk #NeuroAI Annual Conference! Join us on Wed 5 November 2025 at @uclchildhealth.bsky.social Details and registration: www.ucl.ac.uk/event-ticket... Poster and lightning talks submissions are now open, up to 8th Oct. @ucl-neurodomain.bsky.social

Almost last call to register for UK neural computation conference in London July 10-11. Registration deadline is July 1st. We have some great talks and posters as well as a session on funding with ARIA. 🤖🧠🧪 Look forward to seeing you all there. Now click here 👇 neuralcomputation.uk

A cartoon-style illustration of a brain and a computer having a conversation. The brain has eyes and a mouth, and is animated to look like it's talking. It says, 'Have you heard about this comp neuro thing happening at Imperial College?'. The computer has a friendly face on its screen and is replying, 'Yeah it's going to be pretty hot'.

Interested in theoretical neuroscience or machine learning but come from a non-quantitative background? This summer school is for you! Learn the foundational theory needed to excel in a quantitative PhD in 7 weeks. Apply by feb 7!

Gatsby Computational Neuroscience Unit@gatsbyucl.bsky.social · 2y ago

📢 Apply now for the 7-week #Mathematics #SummerSchool in London! You will develop mathematics skills and intuition necessary to enter the #TheoreticalNeuroscience or #MachineLearning field. ℹ️ www.ucl.ac.uk/gatsby/study-and-work/gatsby-bridging-programme Please help spread the word!

Gatsby Bridging Programme flyer

(1/5) Fun fact: Several classic results in the stat. mech. of learning can be derived in a couple lines of simple algebra! In this paper with Haim Sompolinsky, we simplify and unify derivations for high-dimensional convex learning problems using a bipartite cavity method. arxiv.org/abs/2412.01110

Simplified derivations for high-dimensional convex learning problems

Statistical physics provides tools for analyzing high-dimensional problems in machine learning and theoretical neuroscience. These calculations, particularly those using the replica method, often invo...

arxiv.org