<?xml version="1.0" encoding='utf-8'?>
<!DOCTYPE wml PUBLIC "-//WAPFORUM//DTD WML 1.1//EN" "http://www.wapforum.org/DTD/wml_1.1.xml">
<wml>
<card id="card1" title="Geoffrey Hinton - Page 21 - Wikipedia">
<p>
<a accesskey="1" href="page.php?w=Geoffrey_Hinton&amp;p=20">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Geoffrey_Hinton&amp;p=22">3.Next</a>
</p>
<p>Rumelhart came up with the basic idea of backpropagation, so it's his invention." Although this work was important in popularising backpropagation, it was not the first to suggest the approach. Reverse-mode <a href="page.php?w=automatic_differentiation">automatic differentiation</a>, of which backpropagation is a special case, was proposed by <a href="page.php?w=Seppo_Linnainmaa">Seppo Linnainmaa</a> in 1970, and <a href="page.php?w=Paul_Werbos">Paul Werbos</a> proposed to use it to train neural networks in 1974.</p>

<p>In 2017, Hinton co-authored</p><p>
<a accesskey="1" href="page.php?w=Geoffrey_Hinton&amp;p=20">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Geoffrey_Hinton&amp;p=22">3.Next</a>
</p>

<do type="prev" label="Search">
        <go href="search.wml"/>
</do>

</card>
</wml>
