Generative Models: Self-Attention and Transformers

In course

Enim ullamco et dolore tempor ea nulla adipisicing cupidatat officia consequat laboris elit est cupidatat. Pariatur elit sunt ea est nisi exercitation anim esse labore enim velit. Aliqua proident laborum ut qui nulla proident minim nulla. Do officia aliquip quis et aliquip duis laborum est excepteur incididunt Lorem. Qui excepteur consectetur tempor enim amet ut cupidatat in.

Description

This lecture covers generative models focusing on self-attention and transformers. Topics include autoencoders, Boltzmann machines, masked training, attention mechanisms, and maximum entropy principle. The slides discuss sampling methods, empirical means, and correlations in detail.

Instructor

fugiat laborum non

Ut aute enim ullamco est est enim officia laboris dolor magna qui nostrud qui excepteur. Eiusmod non minim exercitation cupidatat commodo proident excepteur deserunt. Pariatur duis aliquip consectetur amet laborum sint dolore ullamco consequat consectetur velit.

Official source

https://mediaspace.epfl.ch/media/0_gepvw60c

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Statistics

Data analysis: Regression analysis

Statistical inference: Mathematical statistics

Data collection: Statistical sampling

Mathematics

Algebra: Linear algebra

Information engineering

Machine learning: Artificial neural networks

Information theory: Channel capacity

Related lectures (528)