<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>thesIt &#187; universal approximation property</title>
	<atom:link href="http://lakm.us/thesit/tag/universal-approximation-property/feed/" rel="self" type="application/rss+xml" />
	<link>http://lakm.us/thesit</link>
	<description>computer science research log in semi microbloging style</description>
	<lastBuildDate>Tue, 24 Aug 2010 21:34:55 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9</generator>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
			<item>
		<title>Approximation Capabilities of Neural Net &#8230;</title>
		<link>http://lakm.us/thesit/296/approximation-capabilities-of-neural-net/</link>
		<comments>http://lakm.us/thesit/296/approximation-capabilities-of-neural-net/#comments</comments>
		<pubDate>Wed, 11 Aug 2010 19:27:51 +0000</pubDate>
		<dc:creator>Arif</dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Enăchescu 2008]]></category>
		<category><![CDATA[neural network]]></category>
		<category><![CDATA[universal approximation property]]></category>

		<guid isPermaLink="false">http://xp-racy.lan/s2/?p=296</guid>
		<description><![CDATA[Approximation Capabilities of Neural Networks. C. Enăchescu, Journal of Numerical Analysis, Industrial and Applied Mathematics (JNAIAM), vol. 3, no. 3-4, 2008, pp. 221-230
From the learning point of view, the approximation of a function is equivalent with the learning problem of a neural network. In this paper we want to show the capabilities of a neural [...]]]></description>
			<content:encoded><![CDATA[<p><em>Approximation Capabilities of Neural Networks</em>. C. Enăchescu, Journal of Numerical Analysis, Industrial and Applied Mathematics (JNAIAM), vol. 3, no. 3-4, 2008, pp. 221-230</p>
<p>From the learning point of view, the approximation of a function is equivalent with the learning problem of a neural network. In this paper we want to show the <b>capabilities</b> of a neural network to approximate <b>arbitrary continuous functions</b>. We have made some experiments in order to confirm the theoretical results.</p>
<p><code><a href="http://www.jnaiam.org/downloads.php?did=56">c48613aed54c29e0f60ca35833aebf70.pdf</a></code></p>
<p><img src="http://lakm.us/thesit/wp-content/uploads/eq_e24d2aedb290ba633f0a3dcdfad9175b.png" align="absmiddle" class="tex" alt="f : X \subseteq R^{n} \to R^{m}" /> is a continuous function</p>
<h2>Neural Network and Best Approximation Theory</h2>
<p>Given <img src="http://lakm.us/thesit/wp-content/uploads/eq_4e2502618686cea51d948c1c919e269c.png" align="absmiddle" class="tex" alt="f \in F" /> and <img src="http://lakm.us/thesit/wp-content/uploads/eq_58592aed1574633ee78fcc785b9df672.png" align="absmiddle" class="tex" alt="A \subseteq F" /> we call the distance of <em>f</em> from <em><strong>A</strong></em> as <img src="http://lakm.us/thesit/wp-content/uploads/eq_e90b15c33b7d0a112bd00cad22fd8841.png" align="absmiddle" class="tex" alt="d(f,A)=inf\left \| f-a \right \|, a\in A" /></p>]]></content:encoded>
			<wfw:commentRss>http://lakm.us/thesit/296/approximation-capabilities-of-neural-net/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>
