<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	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/"
	
	>
<channel>
	<title>
	Comments on: Color Cycle Survey	</title>
	<atom:link href="https://mpetroff.net/2018/12/color-cycle-survey/feed/" rel="self" type="application/rss+xml" />
	<link>https://mpetroff.net/2018/12/color-cycle-survey/</link>
	<description>mpetroff.net</description>
	<lastBuildDate>Sun, 12 Jan 2020 22:24:35 +0000</lastBuildDate>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	
	<item>
		<title>
		By: Matthew Petroff		</title>
		<link>https://mpetroff.net/2018/12/color-cycle-survey/#comment-272794</link>

		<dc:creator><![CDATA[Matthew Petroff]]></dc:creator>
		<pubDate>Mon, 11 Mar 2019 15:14:12 +0000</pubDate>
		<guid isPermaLink="false">https://mpetroff.net/?p=2760#comment-272794</guid>

					<description><![CDATA[In reply to &lt;a href=&quot;https://mpetroff.net/2018/12/color-cycle-survey/#comment-272259&quot;&gt;Niall MacCrann&lt;/a&gt;.

I haven&#039;t had much time to work on the analysis recently, but it&#039;s not far enough along to share much. The neural networks trained in the current analysis definitely do better than random, but they&#039;re currently fairly inconsistent between training runs. I should be able to improve this by refining the analysis, but more data would also be nice.]]></description>
			<content:encoded><![CDATA[<p>In reply to <a href="https://mpetroff.net/2018/12/color-cycle-survey/#comment-272259">Niall MacCrann</a>.</p>
<p>I haven&#8217;t had much time to work on the analysis recently, but it&#8217;s not far enough along to share much. The neural networks trained in the current analysis definitely do better than random, but they&#8217;re currently fairly inconsistent between training runs. I should be able to improve this by refining the analysis, but more data would also be nice.</p>
]]></content:encoded>
		
			</item>
		<item>
		<title>
		By: Niall MacCrann		</title>
		<link>https://mpetroff.net/2018/12/color-cycle-survey/#comment-272259</link>

		<dc:creator><![CDATA[Niall MacCrann]]></dc:creator>
		<pubDate>Thu, 07 Mar 2019 16:55:32 +0000</pubDate>
		<guid isPermaLink="false">https://mpetroff.net/?p=2760#comment-272259</guid>

					<description><![CDATA[This is very cool. Any chance you could post one or more of the current best performing color cycles? I&#039;m finishing off a paper and would be cool to use one of them...]]></description>
			<content:encoded><![CDATA[<p>This is very cool. Any chance you could post one or more of the current best performing color cycles? I&#8217;m finishing off a paper and would be cool to use one of them&#8230;</p>
]]></content:encoded>
		
			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/?utm_source=w3tc&utm_medium=footer_comment&utm_campaign=free_plugin

Page Caching using Disk: Enhanced 
Content Delivery Network via Amazon Web Services: CloudFront: cdn0.mpetroff.net
Minified using Disk

Served from: mpetroff.net @ 2026-03-30 09:34:25 by W3 Total Cache
-->