Simons Institute for the Theory of Computing

California State Senator Jerry McNerney takes questions from the audience. simons.berkeley.edu/workshops/gove… #SimonsLive

Inioluwa Deborah Raji kicks off the workshop on Governance at the Technological Frontier: Translating Research into Policy for AI Oversight. simons.berkeley.edu/workshops/gove… #SimonsLive

Public lecture at @the_IAS today honoring Jim Simons.

Join us! simons.berkeley.edu/workshops/gove…

3/4 Peter's 1996 paper was titled “For valid generalization, the size of the weights is more important than the size of the network.” Telgarsky said: "I just want to emphasize how good of a communicator he is, by putting a theorem as the title of a paper."proceedings.neurips.cc/paper/1996/has…

1/4 Matus Telgarsky of @nyuniversity's Courant Institute on Peter Bartlett’s unique contributions to theoretical ML through the 1990s: “For people like me, who came [into the field] in the 2000s, [his papers were] like a shining light.”

4/4 Matus Telgarsky spoke at the Simons Institute's workshop on Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era, celebrating Peter Bartlett's 60th birthday. simons.berkeley.edu/talks/matus-te…

Join us for a special workshop on Governance at the Technological Frontier: Translating Research into Policy for AI Oversight. Keynotes by California State Senator @jerrymcnerney and @SureshVenkat46. Thursday, 4/30, 1–5:30 p.m. Registration required. simons.berkeley.edu/workshops/gove…

1/3 In 1958, the NY Times wrote about Frank Rosenblatt's perceptron, as an "embryo of computer designed to read and grow wiser." @UCSD's Misha Belkin examined this astonishing claim and came to a surprising conclusion, at a Simons Institute workshop honoring Peter Bartlett's work

3/3 Misha Belkin of @UCSD spoke at the Simons Institute workshop on Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era, celebrating Peter Bartlett's birthday and decades of work in theoretical machine learning. youtube.com/live/xgaZPTG7h…

2/3 "If you look carefully at the perceptron, a lot of modern machine learning just kind of appears, maybe sometimes even in a fairly explicit form," said Misha Belkin of @UCSD. In retrospect, it justified the 1958 NY Times claim that the perceptron was the embryo of modern ML.

"Can AI assist in Mathematics and Computer Science research?" @Berkeley_EECS Colloquium Prabhakar Raghavan @WittedNote, Chief Technologist, @Google 4 – 5 p.m., Wed., April 15 Banatao Auditorium, Sutardja Dai Hall eecs.berkeley.edu/research/collo…

Next week at the Simons Institute, a workshop on Agency in Collaborative Learning. Join us! simons.berkeley.edu/workshops/agen…

Congratulations to our friend and colleague @matei_zaharia on being awarded the ACM Prize in Computing!

Thursday and Friday this week, a workshop on Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era, celebrating Peter Bartlett's 60th birthday. simons.berkeley.edu/workshops/theo…

Please join the AMS in congratulating Charles H. Bennett and Gilles Brassard , who received the 2025 ACM A.M. Turing Award for their essential role in establishing the foundations of quantum information science and transforming secure communication and computing, as announced by @theofficialacm. Read more. Link in comments.