Apurva Ratan Murty
@apurvaratan
Neuroscientist. Assistant Professor of Cognition and Brain Science @GeorgiaTech Prev: Postdoc @MIT, PhD @iiscbangalore
ID: 62186989
http://www.murtylab.com 02-08-2009 03:34:16
626 Tweet
1,1K Followers
1,1K Following
Super excited to share our recent work on privileged representational axes in biological and artificial neural networks! w/ Nancy Kanwisher @[email protected] Josh McDermott Alex Williams biorxiv.org/content/10.110…
What makes humans similar or different to AI? In a new study, led by Florian Mahner and Lukas Muttenthaler and w/ Umut Güçlü, we took a deep look at the factors underlying their representational alignment, with surprising results. arxiv.org/abs/2406.19087 🧵
1/5 Excited to finally share our new paper (led by Laura Driscoll, now a group leader at the Allen!) in Nature Neuroscience on modular computation in neural networks! We've explored how artificial recurrent networks handle multiple tasks, offering insights into flexible computation.
Exciting new work from Doby Rahnev ‘s lab!
do large-scale vision models represent the 3D structure of objects? excited to share our benchmark: multiview object consistency in humans and image models (MOCHI) with Stephanie Fu Yutong Bai Thomas O'Connell Yoni Friedman Nancy Kanwisher @[email protected] Josh Tenenbaum and Alexei Efros 1/👀
If you’re interested in this work, get in touch about joining my lab at University of Illinois Beckman Institute at Illinois ! Tomorrow is my birthday -- if you've read this far, retweet to spread the word!
An excellent thread by Aran Nayebi. Also an important PSA on the relationship between the model dimensionality and ability to predict brain data.