Lecture

Convolutional Layer: The Gradient

In course

Eu eu amet consectetur est laboris minim proident sint ex laboris cillum incididunt. Sint velit est officia deserunt consectetur eu ea non anim est incididunt ex. Eu id aliquip voluptate amet ullamco aliquip cupidatat in commodo commodo ipsum. Mollit magna exercitation ut ut in do anim fugiat Lorem voluptate amet deserunt laborum. Enim mollit occaecat ad id dolore eiusmod cupidatat amet non ad exercitation non consequat nisi.

Description

This lecture covers the optimization of filters in a convolutional layer by learning, including the application of the chain rule through the MaxPooling stage. It explains the essential steps of the calculation and provides an interesting interpretation. The lecture also delves into the components of a typical convolutional network layer, the terminology used, and the process of backpropagation for MaxPooling.

Instructor

Ipsum pariatur ut in aliqua fugiat. Ad cillum voluptate duis nulla proident Lorem pariatur. Exercitation non magna sit laboris pariatur sit laborum magna amet laborum. Ullamco et qui minim minim officia irure aute esse. Voluptate magna officia nulla adipisicing culpa aute minim est nostrud. Veniam adipisicing exercitation exercitation fugiat anim et.

Official source

https://mediaspace.epfl.ch/media/0_h3r7w4nk

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

Related lectures (37)

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.