---
abstract: "We discuss the derivation and implementation of convolutional neural networks, followed by an extension which allows one to learn sparse combinations of feature maps. The derivation we present is specific to two-dimensional data and convolutions, but can be extended without much additional effort to an arbitrary number of dimensions. Throughout the discussion, we emphasize\r\nefficiency of the implementation, and give small snippets of MATLAB code to accompany the equations."
altloc: []
chapter: ~
commentary: ~
commref: ~
confdates: ~
conference: ~
confloc: ~
contact_email: ~
creators_id: []
creators_name:
  - family: Bouvrie
    given: Jake
    honourific: ''
    lineage: ''
date: 2006-11-22
date_type: completed
datestamp: 2007-12-10 21:42:07
department: ~
dir: disk0/00/00/58/69
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 5869
fileinfo: /style/images/fileicons/application_pdf.png;/5869/1/cnn_tutorial.pdf
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: unpub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'convolutional neural networks, machine vision, machine learning'
lastmod: 2011-03-11 08:57:01
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: ~
pubdom: TRUE
publication: ~
publisher: ~
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 22
series: ~
source: ~
status_changed: 2007-12-10 21:42:07
subjects:
  - comp-sci-neural-nets
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: Notes on Convolutional Neural Networks
type: other
userid: 7430
volume: ~
<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>