<?xml version="1.0" encoding="UTF-8"?>
<!-- generator="FeedCreator 1.8" -->
<?xml-stylesheet href="https://wiki.eecs.yorku.ca/lab/MLL/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://wiki.eecs.yorku.ca/lab/MLL/feed.php">
        <title>Machine Learning Lab - projects:fsmn</title>
        <description></description>
        <link>https://wiki.eecs.yorku.ca/lab/MLL/</link>
        <image rdf:resource="https://wiki.eecs.yorku.ca/lab/MLL/_media/wiki:dokuwiki-128.png" />
       <dc:date>2026-05-13T13:20:57+00:00</dc:date>
        <items>
            <rdf:Seq>
                <rdf:li rdf:resource="https://wiki.eecs.yorku.ca/lab/MLL/projects:fsmn:start?rev=1454558788&amp;do=diff"/>
            </rdf:Seq>
        </items>
    </channel>
    <image rdf:about="https://wiki.eecs.yorku.ca/lab/MLL/_media/wiki:dokuwiki-128.png">
        <title>Machine Learning Lab</title>
        <link>https://wiki.eecs.yorku.ca/lab/MLL/</link>
        <url>https://wiki.eecs.yorku.ca/lab/MLL/_media/wiki:dokuwiki-128.png</url>
    </image>
    <item rdf:about="https://wiki.eecs.yorku.ca/lab/MLL/projects:fsmn:start?rev=1454558788&amp;do=diff">
        <dc:format>text/html</dc:format>
        <dc:date>2016-02-04T04:06:28+00:00</dc:date>
        <dc:creator>Anonymous (anonymous@undisclosed.example.com)</dc:creator>
        <title>FSMN</title>
        <link>https://wiki.eecs.yorku.ca/lab/MLL/projects:fsmn:start?rev=1454558788&amp;do=diff</link>
        <description>FSMN

Feedforward Sequential Memory Networks (FSMN)

[ FSMN structure]

Feedforward sequential memory networks (FSMN) is a novel neural network structure to model long-term dependency in time series without using recurrent feedback. The proposed FSMN is a standard fully-connected feedforward neural network equipped with some learnable memory blocks in its hidden layers. The memory blocks use a tapped-delay line structure to encode the long context information into a fixed-size representation as …</description>
    </item>
</rdf:RDF>
