Stanford CS25: V1 I Self Attention and Non-parametric transformers (NPTs)

Aidan is a PhD student at Oxford supervised by Yarin Gal, and one of the cofounders of Cohere. He is fascinated by building massive neural networks and getting them into the hands of more engineers and researchers.

Jannik is a PhD student at the University of Oxford. He is supervised by Yarin Gal and Tom Rainforth. His research interests include Bayesian Deep Learning, Active Learning, and, apparently, building non-parametric models with Transformers.

Neil is a Masters by Research student at the University of Oxford, supervised by Yarin Gal. He is interested in models with relational inductive biases such as Transformers and graph neural networks, as well as Bayesian deep learning.

#NPT

[gilbertobatres-estrada]

Great talk thanks a lot for all your hard work! I am am very impressed the way the transformer architecture is taking over in all areas of deep learning. I am myself working with tabular data and it has been a challenge to find good papers on that area. Recently I have read papers on self attention applied to time series and the results seem promising. I have noticed that some papers address the question on meta learning and zero shot Learning. I think there seems to be a convergence of methods from different disciplines to solve general learning problems.

[divyanshgarg]

Halloween Edition Lecture held on Nov 1

[dertythegrower]

Why is this guy wearing cat ears? Usually its on the headphones people wear as a trend but he has bluetooth headphones so this is very unusual as many noticed.