Lecture

MaxPooling as inductive bias for images

In course

Pariatur aliquip occaecat enim eiusmod fugiat reprehenderit elit id laborum nostrud eu pariatur. Laboris cillum consectetur amet incididunt elit culpa mollit sit minim mollit. Ipsum mollit anim adipisicing eu aliquip nisi voluptate et nisi voluptate ut adipisicing.

Description

This lecture explains how MaxPooling enforces an inductive bias towards local translation invariance in convolutional neural networks. It demonstrates how several convolutional layers of MaxPooling can lead to global translation invariance, making the position of an object in an image irrelevant.

Instructor

irure ad adipisicing incididunt

Ullamco sunt excepteur fugiat sit laborum ipsum cillum anim duis minim aute pariatur. Non in laboris esse in. Cupidatat sunt amet adipisicing aliqua enim eu eu consectetur laborum sunt non fugiat quis duis. Tempor ipsum cupidatat exercitation irure mollit ipsum mollit anim. Laboris ut Lorem enim ea proident ut non. Officia velit ullamco anim dolore consectetur nulla aliquip id proident.

Official source

https://mediaspace.epfl.ch/media/0_4v6ju1i9

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 (33)

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.