<?xml version="1.0" encoding="UTF-8"?>
<!-- generator="FeedCreator 1.8" -->
<?xml-stylesheet href="https://cw.fel.cvut.cz/b232/lib/exe/css.php?s=feed" type="text/css"?>
<rdf:RDF
    xmlns="http://purl.org/rss/1.0/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
    xmlns:dc="http://purl.org/dc/elements/1.1/">
    <channel rdf:about="https://cw.fel.cvut.cz/b232/feed.php">
        <title>CourseWare Wiki courses:bev033dle:labs:lab4_visualization</title>
        <description></description>
        <link>https://cw.fel.cvut.cz/b232/</link>
        <image rdf:resource="https://cw.fel.cvut.cz/b232/lib/tpl/bulma-cw/images/favicon.ico" />
       <dc:date>2026-05-04T14:55:57+0200</dc:date>
        <items>
            <rdf:Seq>
                <rdf:li rdf:resource="https://cw.fel.cvut.cz/b232/courses/bev033dle/labs/lab4_visualization/start?rev=1713376212&amp;do=diff"/>
            </rdf:Seq>
        </items>
    </channel>
    <image rdf:about="https://cw.fel.cvut.cz/b232/lib/tpl/bulma-cw/images/favicon.ico">
        <title>CourseWare Wiki</title>
        <link>https://cw.fel.cvut.cz/b232/</link>
        <url>https://cw.fel.cvut.cz/b232/lib/tpl/bulma-cw/images/favicon.ico</url>
    </image>
    <item rdf:about="https://cw.fel.cvut.cz/b232/courses/bev033dle/labs/lab4_visualization/start?rev=1713376212&amp;do=diff">
        <dc:format>text/html</dc:format>
        <dc:date>2024-04-17T19:50:12+0200</dc:date>
        <dc:creator>Anonymous (anonymous@undisclosed.example.com)</dc:creator>
        <title>courses:bev033dle:labs:lab4_visualization:start</title>
        <link>https://cw.fel.cvut.cz/b232/courses/bev033dle/labs/lab4_visualization/start?rev=1713376212&amp;do=diff</link>
        <description>Quick links: 
 Schedule | 
Forum | 
 BRUTE | 
 Lectures |
 Labs

Lab 5: CNN visualization &amp; adversarial patterns



CNN visualization: deep features, attention maps. Adversarial patterns and attacks

Introduction

In this lab we will consider a CNN classifier and visualize activations and attention maps for its hidden layers, look for input patterns that maximize activations of specific neurons and see how to craft adversarial attacks fooling the network. All of these tasks share very similar te…</description>
    </item>
</rdf:RDF>
