<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Data Science on avanwyk</title>
    <link>https://avanwyk.com/tag/data-science/</link>
    <description>Recent content in Data Science on avanwyk</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>andrich@avanwyk.com (Andrich van Wyk)</managingEditor>
    <webMaster>andrich@avanwyk.com (Andrich van Wyk)</webMaster>
    <copyright>© 2026 Andrich van Wyk</copyright>
    <lastBuildDate>Sun, 14 Apr 2019 11:19:17 +0000</lastBuildDate><atom:link href="https://avanwyk.com/tag/data-science/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>African Antelope: A Case Study of Creating an Image Dataset with FastAI</title>
      <link>https://avanwyk.com/african-antelope-fastai-image-classifier/</link>
      <pubDate>Sun, 14 Apr 2019 11:19:17 +0000</pubDate>
      <author>andrich@avanwyk.com (Andrich van Wyk)</author>
      <guid>https://avanwyk.com/african-antelope-fastai-image-classifier/</guid>
      <description>An end-to-end example of how to create your own image dataset from scratch and train a ResNet50 convolutional neural network for image classification using the FastAI library.</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://avanwyk.com/african-antelope-fastai-image-classifier/feature.jpeg" />
    </item>
    
    <item>
      <title>An Overview of LightGBM</title>
      <link>https://avanwyk.com/an-overview-of-lightgbm/</link>
      <pubDate>Wed, 16 May 2018 21:40:00 +0000</pubDate>
      <author>andrich@avanwyk.com (Andrich van Wyk)</author>
      <guid>https://avanwyk.com/an-overview-of-lightgbm/</guid>
      <description>This post gives an overview of LightGBM and aims to serve as a practical reference. A brief introduction to gradient boosting is given, followed by a look at the LightGBM API and algorithm parameters.</description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://avanwyk.com/an-overview-of-lightgbm/feature.jpeg" />
    </item>
    
    <item>
      <title>Encoding Cyclical Features for Deep Learning</title>
      <link>https://avanwyk.com/encoding-cyclical-features-for-deep-learning/</link>
      <pubDate>Fri, 13 Apr 2018 15:50:24 +0000</pubDate>
      <author>andrich@avanwyk.com (Andrich van Wyk)</author>
      <guid>https://avanwyk.com/encoding-cyclical-features-for-deep-learning/</guid>
      <description>&lt;p&gt;A key concern when dealing with cyclical features is how we can encode the values such that it is clear to the deep learning algorithm that the features occur in cycles.&lt;/p&gt;&#xA;&lt;p&gt;This post looks at a strategy to encode cyclical features in order to clearly express their cyclical nature.&lt;/p&gt;&#xA;</description>
      
    </item>
    
  </channel>
</rss>
