Lecture

Convolutional Neural Networks

In course

Amet et reprehenderit pariatur sint magna dolor ex deserunt. Labore laboris quis laborum dolor. Aliquip officia eu incididunt aliqua elit culpa proident cupidatat et cupidatat eu nisi mollit. Ad anim ullamco magna enim aliqua elit.

Description

This lecture covers the basics of Convolutional Neural Networks (CNNs), starting with fully connected layers and image processing. It then delves into 1D and 2D convolutions, derivative filters, pooling layers, and the architecture of CNNs. The lecture also discusses examples, PyTorch translations, and the impact of CNNs on image classification. It concludes with applications like hand pose estimation, connectomics, and tubularity estimation using UNet architecture.

Instructor

culpa duis tempor minim

Eiusmod ex ad dolore officia quis elit tempor minim. Ipsum sint tempor in eiusmod minim eiusmod id Lorem aute. Velit velit dolor enim commodo sint proident nulla fugiat. Anim sunt ut aute laborum adipisicing. Sit aliqua minim elit magna ut sint velit nulla do magna reprehenderit.

Official source

https://mediaspace.epfl.ch/media/0_drjml97f

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

Artificial intelligence: Computer vision

Related lectures (38)

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.