<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Machine Learning | Hanhui Huang</title><link>https://hanhuihuang.netlify.app/tag/machine-learning/</link><atom:link href="https://hanhuihuang.netlify.app/tag/machine-learning/index.xml" rel="self" type="application/rss+xml"/><description>Machine Learning</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 01 Oct 2022 00:00:00 +0000</lastBuildDate><image><url>https://hanhuihuang.netlify.app/media/icon_hu4c902caa8eff8a8a3b4e0704d580de44_14527_512x512_fill_lanczos_center_3.png</url><title>Machine Learning</title><link>https://hanhuihuang.netlify.app/tag/machine-learning/</link></image><item><title>Automatic morphological analysis of fossils</title><link>https://hanhuihuang.netlify.app/project/automatic-morphological-analysis-of-fossils/</link><pubDate>Sat, 01 Oct 2022 00:00:00 +0000</pubDate><guid>https://hanhuihuang.netlify.app/project/automatic-morphological-analysis-of-fossils/</guid><description>&lt;p>We produced the first large image dataset of fusulinids (2400 images) with the aid of deep learning image segmentation technique (BlendMask)&lt;/p>
&lt;p>We developed a combined method of deep learning and multi-view augmentation for efficient fusulinid image identification reaching &amp;gt;90% accuracy on generic level&lt;/p>
&lt;p>We conducted advanced morphometric analysis for fusulinid taxonomy and phylogeny&lt;/p>
&lt;p>We are developing multi-modal deep learning frameworks to help AI explain how they “think” when classifying fossils.&lt;/p></description></item></channel></rss>