<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>AI on Chase the Devil</title>
		<link>https://31416.org/tags/ai/</link>
		<description>Recent content in AI on Chase the Devil</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Tue, 07 Oct 2025 17:27:00 +0000</lastBuildDate>
		
			<atom:link href="https://31416.org/tags/ai/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Deep Neural Networks and Julia</title>
				<link>https://31416.org/post/deep_neural_networks_and_julia/</link>
				<pubDate>Tue, 07 Oct 2025 17:27:00 +0000</pubDate>
				<guid>https://31416.org/post/deep_neural_networks_and_julia/</guid>
				<description>&lt;p&gt;Recently, I have spent some time on simple neural networks. The idea is to employ them as universal function approximators for some problems appearing in quantitative finance. There are some great papers on it such as the one from &lt;a href=&#34;https://mathematicsinindustry.springeropen.com/articles/10.1186/s13362-019-0066-7&#34;&gt;Liu et al. (2019)&lt;/a&gt; or &lt;a href=&#34;https://arxiv.org/abs/1901.09647&#34;&gt;Horvath et al. (2019) Deep Learning Volatility&lt;/a&gt; or &lt;a href=&#34;https://arxiv.org/abs/2107.01611&#34;&gt;Rosenbaum &amp;amp; Zhang (2021)&lt;/a&gt;.&#xA;Incidentally, I met Liu back when I was finishing my PhD in TU Delft around 2020.&lt;/p&gt;&#xA;&lt;p&gt;I thought I would try out what Julia offers in terms of library for neural networks. Being a very trendy subject, and Julia a modern language for the scientific community, I had imagined the libraris to be of good quality (like the many I have been using in the past). Surprisingly, I was wrong.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
