Convolutional neural network
Type of feedforward neural network
Summary
A convolutional neural network (CNN) is a type of feedforward neural network that learns features via filter optimization. This type of deep learning network has been applied to process and make predictions from many different types of data including text, images and audio. CNNs are the de-facto standard in deep learning-based approaches to computer vision and image processing, and have only recently been replaced—in some cases—by newer architectures such as the transformer.
Originally created by Enterprisey
8/31/2013, 3:20:31 PM
Modified
4/19/2026, 2:40:58 AM
Recent revisions
Undid revision [[Special:Diff/1349327702|1349327702]] by [[Special:Contributions/Mohammad Hijjawi|Mohammad Hijjawi]] ([[User talk:Mohammad Hijjawi|talk]]) [[WP:AISIGNS]] / [[WP:SYNTH]]
/* Receptive fields in the visual cortex */ Adding Needed Citations
/* Video analysis */ ce
/* Applications */ ce
/* top */ tautology
/* See also */
use named ref to avoid dup
name duplicate ref
/* Distinguishing features */
/* Distinguishing features */
Explained input processing and output generation in fully connected layers
Clarified locally connected layers' independent learning
Added pmc. Removed URL that duplicated identifier. | [[:en:WP:UCB|Use this bot]]. [[:en:WP:DBUG|Report bugs]]. | Suggested by Headbomb | #UCB_toolbar
Altered template type. Added biorxiv. Removed URL that duplicated identifier. Removed access-date with no URL. Removed parameters. Some additions/deletions were parameter name changes. | [[:en:WP:UCB|Use this bot]]. [[:en:WP:DBUG|Report bugs]]. | Suggested by Headbomb | #UCB_toolbar
clean up cite biorxiv
Alter: date, pages. Add: pages, pmc, pmid, doi-access, article-number, bibcode, authors 1-1. Removed URL that duplicated identifier. Removed parameters. Some additions/deletions were parameter name changes. | [[:en:WP:UCB|Use this bot]]. [[:en:WP:DBUG|Report bugs]]. | Suggested by Headbomb | #UCB_toolbar
Adds Animal behavior detection subsection
match page name
/* top */
