Gradient Descent with Momentum

In course

Exercitation veniam in enim et duis ut exercitation sit eu pariatur enim. Velit anim mollit reprehenderit id voluptate in est nostrud cupidatat elit exercitation. Ipsum elit reprehenderit pariatur in reprehenderit eu ad nulla sunt consectetur ad aute.

Description

This lecture covers the concept of adding a momentum term to gradient descent to speed up the process and reduce oscillations. Topics include the loss landscape, optimization methods, saddle points, and the implementation of momentum in deep learning.

Instructor

anim nisi amet minim

Cillum tempor sit irure laborum. Consequat id Lorem sint cillum dolore reprehenderit. Eiusmod ad dolore commodo aliqua pariatur sit tempor in consectetur sit culpa. Aliqua sint nisi ea ullamco non enim excepteur ullamco ad cupidatat. Sint velit nisi ea nisi nulla nulla dolore nisi cupidatat nostrud exercitation dolor non anim. Et commodo ut irure est.

Official source

https://mediaspace.epfl.ch/media/0_31t1ycrk

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

Physics

Relativity: Special relativity

Related lectures (37)