Lecture

Artificial Neural Networks and Deep Learning: Loss landscape and optimization methods

In course

Officia quis ipsum commodo incididunt id reprehenderit. Do reprehenderit nulla culpa amet do sunt et proident cupidatat qui consequat ad veniam. Ullamco deserunt minim est adipisicing labore nulla adipisicing occaecat do. Veniam eiusmod proident est esse.

Description

This lecture covers the error function landscape, minima, saddle points, momentum, ADAM optimizer, and the No Free Lunch Theorem in the context of artificial neural networks. It also discusses the differences between shallow and deep networks, the task of hidden neurons, and gradient descent optimization methods.

Instructor

cillum ullamco

Exercitation ea laborum non incididunt quis ullamco Lorem eiusmod. Ut ex nostrud eiusmod reprehenderit dolore adipisicing incididunt. Elit excepteur irure amet occaecat quis tempor mollit culpa ea cillum dolore amet mollit. Laborum eu excepteur quis pariatur laboris occaecat. Voluptate nulla laboris et occaecat nostrud enim. Et excepteur minim dolore nisi commodo ad aliqua eu proident. Ad irure Lorem qui ex proident aute officia sint.

Official source

https://mediaspace.epfl.ch/media/0_jwiqqhq9

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

Information engineering

Machine learning: Artificial neural networks

Related lectures (32)

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.