<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>unsupervised learning | Georgios Exarchakis</title><link>https://exarchakis.net/tag/unsupervised-learning/</link><atom:link href="https://exarchakis.net/tag/unsupervised-learning/index.xml" rel="self" type="application/rss+xml"/><description>unsupervised learning</description><generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><copyright>© 2026</copyright><lastBuildDate>Tue, 04 Oct 2022 14:57:50 +0000</lastBuildDate><image><url>https://exarchakis.net/media/icon_hua2ec155b4296a9c9791d015323e16eb5_11927_512x512_fill_lanczos_center_2.png</url><title>unsupervised learning</title><link>https://exarchakis.net/tag/unsupervised-learning/</link></image><item><title>Efficient spatio-temporal feature clustering for large event-based datasets</title><link>https://exarchakis.net/publication/efficient-spatio-temporal-feature-clustering-for-large-event-based-datasets/</link><pubDate>Tue, 04 Oct 2022 14:57:50 +0000</pubDate><guid>https://exarchakis.net/publication/efficient-spatio-temporal-feature-clustering-for-large-event-based-datasets/</guid><description/></item><item><title>ProSper - A Python Library for Probabilistic Sparse Coding with Non-Standard Priors and Superpositions</title><link>https://exarchakis.net/publication/prosper/</link><pubDate>Mon, 19 Aug 2019 13:48:09 +0300</pubDate><guid>https://exarchakis.net/publication/prosper/</guid><description/></item><item><title>Truncated Variational Sampling for ‘Black Box’ Optimization of Generative Models</title><link>https://exarchakis.net/publication/truncated-variational-sampling-for-black-box-optimization-of-generative-models/</link><pubDate>Sat, 30 Jun 2018 14:38:58 +0200</pubDate><guid>https://exarchakis.net/publication/truncated-variational-sampling-for-black-box-optimization-of-generative-models/</guid><description/></item><item><title>Discrete Sparse Coding</title><link>https://exarchakis.net/publication/discrete-sparse-coding/</link><pubDate>Wed, 01 Nov 2017 00:00:00 +0000</pubDate><guid>https://exarchakis.net/publication/discrete-sparse-coding/</guid><description>&lt;!-- More detail can easily be written here using *Markdown* and $\rm \LaTeX$ math code. --></description></item><item><title>Probabilistic Models for Invariant Representations and Transformations</title><link>https://exarchakis.net/publication/probabilistic-models-for-invariant-representations-and-transformations/</link><pubDate>Thu, 01 Dec 2016 00:00:00 +0000</pubDate><guid>https://exarchakis.net/publication/probabilistic-models-for-invariant-representations-and-transformations/</guid><description>&lt;!-- More detail can easily be written here using *Markdown* and $\rm \LaTeX$ math code. --></description></item><item><title>What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach</title><link>https://exarchakis.net/publication/what-are-the-invariant-occlusive-components-of-image-patches-a-probabilistic-generative-approach/</link><pubDate>Thu, 05 Dec 2013 00:00:00 +0000</pubDate><guid>https://exarchakis.net/publication/what-are-the-invariant-occlusive-components-of-image-patches-a-probabilistic-generative-approach/</guid><description>&lt;!-- More detail can easily be written here using *Markdown* and $\rm \LaTeX$ math code. --></description></item><item><title>Ternary Sparse Coding</title><link>https://exarchakis.net/publication/ternary-sparse-coding/</link><pubDate>Mon, 18 Jun 2012 18:29:37 +0200</pubDate><guid>https://exarchakis.net/publication/ternary-sparse-coding/</guid><description/></item><item><title>Discrete Symmetric Priors for Sparse Coding</title><link>https://exarchakis.net/publication/discrete-symmetric-priors-for-sparse-coding/</link><pubDate>Tue, 04 Oct 2011 00:00:00 +0000</pubDate><guid>https://exarchakis.net/publication/discrete-symmetric-priors-for-sparse-coding/</guid><description>&lt;!-- More detail can easily be written here using *Markdown* and $\rm \LaTeX$ math code. --></description></item></channel></rss>