Professor at the Gatsby Unit and Sainsbury Wellcome Centre, UCL, trying to figure out how we learn
Andrew Saxe
Loading...
1/7 Excited to share my last PhD article, just accepted to ICML 2026! In it, we (me, Alexandre Payeur, Guillaume Lajoie) used dynamical systems theory to study "local" learning in linear recurrent neural networks. See link for the paper, and thread for a brief summary. arxiv.org/abs/2606.00243
Come chat about this @iclr-conf.bsky.social!
Friday 3:15 PM, Pavilion 4, Poster #4216
Weāve got an exciting new thing to share! We have causal evidence (using TMR) that memory reactivation during sleep promotes abstract understanding of underlying structure, allowing transfer learning in a new domain with zero superficial feature overlap with the learned one.
New preprint! š§
How do RNNs learn abstract rules from sequences, independent of specific stimuli?
By Vezha Boboeva, with Alberto Pezzotta & George Dimitriadis
"From sequences to schemas: low-rank recurrent dynamics underlie abstract relational representations"
www.biorxiv.org/content/10.6...
Two Analytical Connectionism-related updates:
1. ā° 1 week left to apply! Interested in language + AI & cognition? Donāt miss it: www.analytical-connectionism.net/school/2026/
2. š Lecture notes from the first two editions are finally out: proceedings.mlr.press/v320/
Weāre hiring a Group Leader!
Join us to lead a transformative initiative in human systems neuroscience.
Find out more and apply ⤵ļø
www.sainsburywellcome.org/content/curr...
Postdoc opening!
Come work with us on deep learning theory relevant to AI safety
Deadline: 7 Apr 2026
Details and application: www.ucl.ac.uk/work-at-ucl/...
Very excited by this year's Analytical Connectionism Summer School!
A dream lineup of speakers on the topic of language acquisition in minds and machines
Bursaries available to cover costs
Aug 17 ā Aug 28, 2026 Gothenburg
Details: www.analytical-connectionism.net//school/2026/
A great entry into the proposals available for physiologically plausible gradient descent!
I think the way they use dendrite targeting inhibition in this model is particularly elegant.
Time to start testing these ideas folks!!!
#neuroscience š§Ŗ #NeuroAI
The First 1,000 Days (1kD) Project - Collecting and Analyzing an Ultra-Dense Naturalistic Dataset of Human Baby Development https://www.biorxiv.org/content/10.64898/2026.03.19.712982v1