Theory of trained RNNs that interpolates between the classic chaotic solution and a strongly task-adapted solution. Perhaps the best description of motor cortex is in-between. Great collaboration with @david-g-clark.bsky.social, @jzv.bsky.social with supervision by the great @cpehlevan.bsky.social!
Come by at Neurips to hear Hamza present about properties of various feature learning infinite parameter limits of transformer models.
Poster in Hall A-C #4804 at 11 AM PST
Paper arxiv.org/abs/2405.15712 , code github.com/Pehlevan-Gro...
Work with Hamza Chaudhry and @cpehlevan.bsky.social
Applying to do a postdoc or PhD in theoretical ML or neuroscience this year? Consider joining my group (starting next Fall) at UT Austin!
POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
Blake Bordelon
Blake Bordelon
Blake Bordelon
I am totally pumped about this new work . "Task-trained RNNs" are a powerful and influential framework in neuroscience, but have lacked a firm theoretical footing. This work provides one, and makes direct contact with the classical theory of random RNNs:
www.biorxiv.org/content/10.6...
