Reposted by Thomas Miconirev. howard arson @theophite.bsky.social · 09/09/2025it's sad that the UK doesn't have Mormons, because they would be incredible at Taskmaster 71002
Thomas Miconi @thomasmiconi.bsky.social · 17/06/2025What are good examples of meta-training *plastic* neural networks (either optimizing plasticity rules or network structure) to address neurosci questions? Stuff like @tpvogels.bsky.social & @bconfavreux.bsky.social’s rule search, Tyulmankov Neuron 2021, our stuff on transitive inference etc. 030
Thomas Miconi @thomasmiconi.bsky.social · 12/06/2025Google Meet is down A million meetings cancelled The people exult 020
Thomas Miconi @thomasmiconi.bsky.social · 15/05/2025tl;dr: DeepMind automates the Graduate Student Descent algorithm! 100
Thomas Miconi @thomasmiconi.bsky.social · 30/03/2025Really struck at how @tyrellturing.bsky.social model of hippocampus (yesterday at Cosyne) is almost symmetric to the very similar Whittington/Fiete lab models. Latter is based on grid cells, former has no grid cells at all! 010
Thomas Miconi @thomasmiconi.bsky.social · 28/03/2025Max Bennett’s keynote was, predictably, spectacular 🤯 010
Thomas Miconi @thomasmiconi.bsky.social · 26/03/2025I’m off to Montréal for Cosyne 2025. Say hi if you see me! 010
Thomas Miconi @thomasmiconi.bsky.social · 17/01/2025Now out in @NatureNeuro! Animals can do Transitive Inference (TI): quickly learn, and reconfigure, global order from partial info (learn A>B, B>C,C>D, immediately know A>D). But currently no neural model explains the observed features of TI. So we asked the machine to find one for us -and it did! 071
Thomas Miconi @thomasmiconi.bsky.social · 11/12/2024I’m at NeurIPS! Say hi if you want to talk about meta-learning, computational neuroscience, plastic neural networks, or any combination of the above. 050
Reposted by Thomas MiconiFernanda Ferreira @fernandaedi.bsky.social · 30/09/2023There’s a special place in hell for departments that require letters of recommendation for all job applicants rather than just those who make some initial cut. 7707
