Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Clustering with Deep Learning: Taxonomy and New Methods
Elie Aljalbout, Vladimir Golkov, Yawar Siddiqui, Daniel Cremers
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Clustering is a fundamental machine learning method. The quality of its results is dependent on the data distribution. For this reason, deep neural networks can be used for learning better representations of the data. In this paper, we propose a systematic taxonomy for clustering with deep learning, in addition to a review of methods from the field. Based on our taxonomy, creating new methods is more straightforward. We also propose a new approach which is built on the taxonomy and surpasses some of the limitations of some previous work. Our experimental evaluation on image datasets shows that the method approaches state-of-the-art clustering quality, and performs better in some cases.
TL;DR:Unifying framework to perform clustering using deep neural networks
Keywords:clustering, deep learning, neural networks
Enter your feedback below and we'll get back to you as soon as possible.