Surya Ganguli
banner
suryaganguli.bsky.social
Surya Ganguli
@suryaganguli.bsky.social
Professor of Applied Physics at Stanford | Venture Partner a16z | Research in AI, Neuroscience, Physics
It’s actually deep learning with a single weight layer, single output, linear unit, and squared loss. 😇
November 5, 2025 at 3:32 AM
Feel free to quote and include my handle/name. Again, big fan!
October 13, 2025 at 10:35 PM
One delay is that they are fed lies that tariffs are paid for by other countries. But hopefully they will figure it out…
August 2, 2025 at 1:49 PM
Isn’t it just deep learning with a single layer, single output, and squared loss? 😉
July 7, 2025 at 3:11 PM
Now you know how I feel about those brain is a computer discussions :)
July 3, 2025 at 8:28 PM
I’m with @timothyoleary.bsky.social on this one :) and I’ll double down: every biologically plausible deterministic neuron model is a mean field dynamical system that averages out unobserved degrees of freedom 😉
July 3, 2025 at 7:08 PM
So sorry! Hope everything will okay!
June 20, 2025 at 1:02 AM
Love Cargese!
June 19, 2025 at 4:29 PM
Reposted by Surya Ganguli
Next was an fascinating talk by @suryaganguli.bsky.social on theories of learning, with some incredible experiments with mice at the @kempnerinstitute.bsky.social www.youtube.com/watch?v=jLmK... (5/18)
Theories of Learning, Imagination and Reasoning: of Mice and Machines with Surya Ganguli
YouTube video by Kempner Institute at Harvard University
www.youtube.com
June 7, 2025 at 3:12 AM