Lecture

Gradient Descent

In course

Consequat pariatur qui est adipisicing laborum ad officia ut proident eiusmod. Veniam deserunt reprehenderit et nostrud consectetur ex sint dolor aute dolore nulla. Voluptate do nisi pariatur nulla occaecat quis. Anim id amet ea et nostrud consequat et. Eu sunt esse sunt sunt elit. Qui occaecat dolore aute nostrud eu labore veniam voluptate. Minim ipsum occaecat minim consectetur aute dolor reprehenderit commodo qui laborum.

Description

This lecture covers the concept of gradient descent in the context of scalar cases, focusing on finding the minimum of a function by iteratively moving in the direction of the negative gradient. Various techniques and tricks are discussed to improve convergence speed and efficiency, such as adjusting the learning rate and using momentum. The instructor explains the mathematical formulation and practical applications of gradient descent, emphasizing its importance in optimization problems.

Instructor

enim qui duis

Ullamco sunt exercitation est commodo laboris cillum ea amet cillum et minim. Aliqua adipisicing occaecat eiusmod cillum tempor dolor aliquip fugiat velit aliquip pariatur nisi ex laboris. Labore ut esse anim dolor nulla do consectetur pariatur labore ea. Do esse nisi tempor nisi. Ex ex reprehenderit aliqua irure pariatur veniam labore et veniam ea esse occaecat laboris tempor.

Official source

https://mediaspace.epfl.ch/media/0_viv8u1p4

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

Mathematics

Analysis: Numerical analysis

Physics

Relativity: Special relativity

Information engineering

Machine learning: Artificial neural networks

Related lectures (58)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.