Deep Embedded SOM: Joint Representation Learning and Self-Organization. Forest, F., Lebbah, M., Azzag, H., & Lacaille, J. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2019.
Deep Embedded SOM: Joint Representation Learning and Self-Organization [link]Link  Deep Embedded SOM: Joint Representation Learning and Self-Organization [pdf]Paper  Deep Embedded SOM: Joint Representation Learning and Self-Organization [pdf]Slides  Deep Embedded SOM: Joint Representation Learning and Self-Organization [link]Code  abstract   bibtex   
In the wake of recent advances in joint clustering and deep learning, we introduce the Deep Embedded Self-Organizing Map, a model that jointly learns representations and the code vectors of a self-organizing map. Our model is composed of an autoencoder and a custom SOM layer that are optimized in a joint training procedure, motivated by the idea that the SOM prior could help learning SOM-friendly representations. We eval- uate SOM-based models in terms of clustering quality and unsupervised clustering accuracy, and study the benefits of joint training.

Downloads: 0