I am currently a Research Scientist at FAIR at Meta, having fun with the physics of machine learning. {Prior to all that, I attended UCSB College of Creative ...
Non-Gaussian processes and neural networks at finite widths S Yaida Mathematical and Scientific Machine Learning, 165-192, 2020
Sho Yaida
Physics researcher · shoyaida.com
Education: Stanford University (2005–2011) and University of California, Santa Barbara (2002–2005)
Sho is a research scientist at Facebook AI Research (FAIR), focusing on the physics of machine learning. He studied black holes while earning his Ph.D. ...
S. Yaida, ''Non-Gaussian processes and neural networks at finite widths,'' Mathematical and Scientific Machine Learning (2020) [Proceedings; arXiv].
On Friday in the ML Theory Seminar, Sho Yaida (Facebook) will tell us about theoretically analyzing finite-width deep nets. As usual, see https://mltheory.org/# ...
Sho Yaida · 2005-2011. PHD, Stanford U., Phys. Dept. · 2002-2005. UNDERGRADUATE, UC, Santa Barbara.
Aug 15, 2023 · Effective Theory of Transformers Sho Yaida, Research Scientist, Meta Large neural networks perform extremely well in practice, providing the ...
Apr 25, 2024 · List of computer science publications by Sho Yaida.
Sho Yaida. Research Scientist, Meta. Joined September 2018. Names. Sho Yaida (Preferred). Suggest Name. Emails. ****@fb.com (Confirmed). Suggest Email ...