Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels
Alexey Romanov, Anna Rumshisky
Feb 17, 2017 (modified: Mar 30, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:Learning a better representation with neural networks is a challenging problem, which was tackled extensively from different prospectives in the past few years. In this work, we focus on learning a representation that could be used for clustering and introduce a novel loss component that substantially improves the quality of produced clusters, is simple to apply to an arbitrary cost function, and does not require a complicated training procedure.
TL;DR:A novel loss component that leads to substantial improvement of KMeans clustering over the learned representations.
Enter your feedback below and we'll get back to you as soon as possible.