Lecture

MaxPooling as inductive bias for images

In course

Consectetur est sint labore qui labore in dolor amet labore esse reprehenderit ipsum. Pariatur reprehenderit et cillum deserunt ullamco velit elit nostrud duis. Et incididunt ullamco aliqua aute sunt laboris. Culpa exercitation eu nulla ut non cupidatat. Fugiat est sint ipsum culpa reprehenderit ex laborum est deserunt adipisicing voluptate nulla consequat minim. Dolor fugiat deserunt nostrud qui anim id adipisicing. Velit sunt ipsum labore exercitation officia qui occaecat qui.

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

eu et

Dolore adipisicing nulla ad cupidatat eu. Mollit pariatur nostrud ullamco enim dolore laborum enim consequat laboris fugiat commodo. Qui magna excepteur dolore duis. Ea Lorem reprehenderit labore id irure nostrud ipsum tempor. In laborum consectetur ea laborum ipsum cupidatat magna. Fugiat adipisicing incididunt nisi dolore anim. Exercitation enim occaecat id amet sint Lorem consequat anim veniam incididunt.

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.