<?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="Stochastic gradient descent - Page 22 - Wikipedia">
<p>
<a accesskey="1" href="page.php?w=Stochastic_gradient_descent&amp;p=21">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Stochastic_gradient_descent&amp;p=23">3.Next</a>
</p>
<p>Waveform Inversion (FWI).</p>

<p>Stochastic gradient descent competes with the <a href="page.php?w=limited-memory_BFGS">L-BFGS</a> algorithm, which is also widely used. Stochastic gradient descent has been used since at least 1960 for training <a href="page.php?w=linear_regression">linear regression</a> models, originally under the name <a href="page.php?w=ADALINE">ADALINE</a>.</p>

<p>Another stochastic gradient descent algorithm is the <a href="page.php?w=Least_mean_squares_filter">least mean squares (LMS)</a> adaptive filter.</p>

<p><big>Extensions and variants</big></p><p>
<a accesskey="1" href="page.php?w=Stochastic_gradient_descent&amp;p=21">1.Previous</a><br />
<a accesskey="3" href="page.php?w=Stochastic_gradient_descent&amp;p=23">3.Next</a>
</p>

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

</card>
</wml>
