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]](https://bibbase.org/img/filetypes/link.svg "link")
Link ![Deep Embedded SOM: Joint Representation Learning and Self-Organization [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper Slides Code abstract bibtex 103 downloads
Link Paper Slides Code abstract bibtex 103 downloads 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.
@inproceedings{forest2019deepembedded,
abstract = {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.},
author = {Forest, Florent and Lebbah, Mustapha and Azzag, Hanane and Lacaille, J{\'{e}}r{\^{o}}me},
booktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},
keywords = {autoencoder,clustering,deep learning,representation learning,self-organizing map},
title = {{Deep Embedded SOM: Joint Representation Learning and Self-Organization}},
year = {2019},
url_Link = {https://www.esann.org/proceedings/2019},
url_Paper = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-30.pdf},
url_Slides = {ESANN-2019-DeepEmbeddedSOM-pres.pdf},
url_Code = {https://github.com/FlorentF9/DESOM},
bibbase_note = {<img src="assets/img/papers/desom-maps.png">}
}Downloads: 103
{"_id":"NZesn7FwN5hCifhh5","bibbaseid":"forest-lebbah-azzag-lacaille-deepembeddedsomjointrepresentationlearningandselforganization-2019","authorIDs":["3RZwrfhgEfG63k5jg","3SxonBqsacbDvLJ76","4pjW5cyboi9zAMzpJ","5GQkZSCvSenq46qrN","5e6b9bc538517edf01000017","5yiWY47jSKdKfxe8h","9qSGhPLL995WCyBt4","AKaMxQWEWqbjcWG7N","AM9C2xF5khaf9AsvW","AxC6pWiCeJw6FYXPE","CaDeWzaiZSQLxHvcA","DoEx226svswhqRcaE","ELezCHnS9s4GLdQy6","FzQCQZZM2MyWCZ2Nk","LbHvNbjvd5SkFkuNR","PGMnjRbz468bY8K45","PMuH6kGJyGBBKaPYe","QKR8LH5fNTeez9B9D","QooEurLXqaPJTygeA","Shf2NXF4PRiWmkkaR","TLEpmitPf4iQZYYH3","XJuBB3DfhZqz5JRA2","XQYrXit4PKWKPpoFZ","Y9BDNsRff4jtL7KXf","ZJz7PJ2gTd3c9R5Me","ZP68aFMeNEEHE8xxP","ZdhbKf5hqQGmmgznz","bSZr8LpgDyfBqdthh","cWw2GCMAZjb3jNqJg","fqKhgaj4PXP3S7gdz","gin9q4MZJiqC4ijLj","hsKzafbbbN8QCZpaJ","nXg8oPeomTivMAv3c","osQRFxHgsbu3kMKhA","qg2SiAD87Cvt74rRz","rXGN6qAzjYH3w7cDb","rsGH8RBJrySfARcn6","ubSLXJFk5Lfp3hBSJ","v25LmrsFxX427ebY9","wqoh86YAdKofyck7L","xJ6yoMkx7j8uqjRS6","ysCctvEZbBsFvn8e7"],"author_short":["Forest, F.","Lebbah, M.","Azzag, H.","Lacaille, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"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.","author":[{"propositions":[],"lastnames":["Forest"],"firstnames":["Florent"],"suffixes":[]},{"propositions":[],"lastnames":["Lebbah"],"firstnames":["Mustapha"],"suffixes":[]},{"propositions":[],"lastnames":["Azzag"],"firstnames":["Hanane"],"suffixes":[]},{"propositions":[],"lastnames":["Lacaille"],"firstnames":["Jérôme"],"suffixes":[]}],"booktitle":"European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)","keywords":"autoencoder,clustering,deep learning,representation learning,self-organizing map","title":"Deep Embedded SOM: Joint Representation Learning and Self-Organization","year":"2019","url_link":"https://www.esann.org/proceedings/2019","url_paper":"https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-30.pdf","url_slides":"ESANN-2019-DeepEmbeddedSOM-pres.pdf","url_code":"https://github.com/FlorentF9/DESOM","bibbase_note":"<img src=\"assets/img/papers/desom-maps.png\">","bibtex":"@inproceedings{forest2019deepembedded,\nabstract = {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.},\nauthor = {Forest, Florent and Lebbah, Mustapha and Azzag, Hanane and Lacaille, J{\\'{e}}r{\\^{o}}me},\nbooktitle = {European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},\nkeywords = {autoencoder,clustering,deep learning,representation learning,self-organizing map},\ntitle = {{Deep Embedded SOM: Joint Representation Learning and Self-Organization}},\nyear = {2019},\nurl_Link = {https://www.esann.org/proceedings/2019},\nurl_Paper = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-30.pdf},\nurl_Slides = {ESANN-2019-DeepEmbeddedSOM-pres.pdf},\nurl_Code = {https://github.com/FlorentF9/DESOM},\nbibbase_note = {<img src=\"assets/img/papers/desom-maps.png\">}\n}\n\n","author_short":["Forest, F.","Lebbah, M.","Azzag, H.","Lacaille, J."],"key":"forest2019deepembedded","id":"forest2019deepembedded","bibbaseid":"forest-lebbah-azzag-lacaille-deepembeddedsomjointrepresentationlearningandselforganization-2019","role":"author","urls":{" link":"https://www.esann.org/proceedings/2019"," paper":"https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2019-30.pdf"," slides":"http://florentfo.rest/files/ESANN-2019-DeepEmbeddedSOM-pres.pdf"," code":"https://github.com/FlorentF9/DESOM"},"keyword":["autoencoder","clustering","deep learning","representation learning","self-organizing map"],"metadata":{"authorlinks":{"forest, f":"https://florentfo.rest/publications"}},"downloads":103},"bibtype":"inproceedings","creationDate":"2020-03-13T14:42:13.968Z","downloads":103,"keywords":["autoencoder","clustering","deep learning","representation learning","self-organizing map"],"search_terms":["deep","embedded","som","joint","representation","learning","self","organization","forest","lebbah","azzag","lacaille"],"title":"Deep Embedded SOM: Joint Representation Learning and Self-Organization","year":2019,"biburl":"http://florentfo.rest/files/publications.bib","dataSources":["pBkCjKbyeirr5jeAd","DgnR6pzJ98ZEp97PW","2puawT8ZAQyYRypA3","6rNfa4Kp6dL5sGmf5","xH8ySTsEPTLou9gyR"]}