The Quarks of Attention

Add to your list(s) Download to your calendar using vCal

• Professor Pierre Baldi - Distinguished Professor, Department of Computer Science Director, Institute for Genomics and Bioinformatics Associate Director, Center for Machine Learning and Intelligent Systems, University of California, Irvine
• Wednesday 26 January 2022, 15:05-15:55
• Online.

If you have a question about this talk, please contact Ben Karniely.

Attention plays a fundamental role in both natural and artificial intelligence systems. In deep learning, several attention-based neural network architectures have been proposed to tackle problems in natural language processing (NLP) and beyond, including transformer architectures which currently achieve state-of-the-art performance in NLP tasks. In this presentation we will: 1) identify and classify the most fundamental building blocks (quarks) of attention, both within and beyond the standard model of deep learning; 2) identify how these building blocks are used in all current attention-based architectures, including transformers; 3) demonstrate how transformers can effectively be applied to new problems in physics, from particle physics to astronomy; and 4) present a mathematical theory of attention capacity where, paradoxically, one of the main tools in the proofs is itself an attention mechanism.

Link to join: https://cl-cam-ac-uk.zoom.us/j/97767639783?pwd=T09GcVJxZUNEUFEvRnZnbWwxeEwzQT09

A recording of this talk is available at the following link: https://www.cl.cam.ac.uk/seminars/wednesday/video/

This talk is part of the Wednesday Seminars - Department of Computer Science and Technology series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Online
• School of Technology
• Trust & Technology Initiative - interesting events
• Wednesday Seminars - Department of Computer Science and Technology
• bld31
• computer science
• se393's list

Note that ex-directory lists are not shown.