150 Western Avenue, Allston, MA 02134

https://iacs.seas.harvard.edu/event/quarks-attention
View map Free Event

RSVP HERE: https://forms.gle/smSKw4ARugNSZMwM7
Abstract: 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. 

  • Sumit Sinha

1 person is interested in this event