Lecture

MaxPooling as inductive bias for images

In course
DEMO: culpa do ut enim
Dolor proident voluptate labore deserunt magna esse aliquip in proident. Aliquip laborum ex nisi et ex deserunt pariatur veniam. Veniam aute est exercitation reprehenderit eu.
Login to see this section
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
laborum cupidatat
Magna amet tempor non duis id ullamco aute adipisicing. Ad est quis fugiat nulla ipsum sint in aliquip incididunt aliquip ea Lorem eu ex. Proident occaecat anim cillum irure irure consectetur ex occaecat aliquip. Cillum duis duis nostrud tempor consequat excepteur qui do nisi ipsum aute. Dolore ea ea ad exercitation ea amet. Aute ut occaecat ad voluptate exercitation eiusmod ea quis. Cillum enim consectetur ea exercitation id.
Login to see this section
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.
Related lectures (33)
NFNets: Removing BatchNorm for High-Performance Image Recognition
Explores NFNets as an alternative to BatchNorm in ResNets, achieving high performance on ImageNet.
Neural Networks: Multilayer Learning
Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.
Convolutional Neural Networks: Fundamentals
Covers the basics of Convolutional Neural Networks, including training optimization, layer structure, and potential pitfalls of summary statistics.
Deep Learning Fundamentals
Introduces the fundamentals of deep learning, covering neural networks, CNNs, special layers, weight initialization, data preprocessing, and regularization.
Visual Intelligence: Machines and Minds
Explores visual intelligence, image formation, computer vision, and representation understanding in machines and minds.
Show more

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.