<?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="Neural network (machine learning) - Page 15 - Wikipedia">
<p>
<a accesskey="1" href="page.php?w=Neural_network_(machine_learning)&amp;p=14">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Neural_network_%28machine_learning%29&amp;p=16">3.Next</a>
</p>
<p>during the late 1960s and 1970s.</p>

<p><big> 1960s and 1970s</big></p>
<p>Fundamental research was conducted on NNs in the 1960s and 1970s. The first working deep learning algorithm was the <a href="page.php?w=group_method_of_data_handling">group method of data handling</a>, a method to train arbitrarily deep neural networks, published by <a href="page.php?w=Alexey_Ivakhnenko">Alexey Ivakhnenko</a> and Valentin Lapa in the <a href="page.php?w=Soviet_Union">Soviet Union</a> (1965). They regarded it as a form of <a href="page.php?w=polynomial_regression">polynomial regression</a>,</p><p>
<a accesskey="1" href="page.php?w=Neural_network_(machine_learning)&amp;p=14">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Neural_network_%28machine_learning%29&amp;p=16">3.Next</a>
</p>

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

</card>
</wml>
