@inproceedings{forest2019deeparchitectures,
abstract = {Recent research has demonstrated how deep neural networks are able to learn representations to improve data clustering. By considering representation learning and clustering as a joint task, models learn clustering-friendly spaces and achieve superior performance, com- pared with standard two-stage approaches where dimensionality reduc- tion and clustering are performed separately. We extend this idea to topology-preserving clustering models, known as self-organizing maps (SOM). First, we present the Deep Embedded Self-Organizing Map (DE- SOM), a model composed of a fully-connected autoencoder and a custom SOM layer, where the SOM code vectors are learnt jointly with the au- toencoder weights. Then, we show that this generic architecture can be extended to image and sequence data by using convolutional and recur- rent architectures, and present variants of these models. First results demonstrate advantages of the DESOM architecture in terms of cluster- ing performance, visualization and training time.},
author = {Forest, Florent and Lebbah, Mustapha and Azzag, Hanane and Lacaille, J{\'{e}}r{\^{o}}me},
booktitle = {Workshop on Learning Data Representations for Clustering (LDRC), PAKDD},
doi = {10.1007/978-3-030-26142-9_10},
keywords = {autoencoder,clustering,deep learning,representation learning,self-organizing map},
title = {{Deep Architectures for Joint Clustering and Visualization with Self-Organizing Maps}},
year = {2019},
url_Link = {https://link.springer.com/chapter/10.1007/978-3-030-26142-9_10},
url_Paper = {LDRC-2019-DeepArchitecturesJointClusteringVisualization-full-paper.pdf},
bibbase_note = {<img src="assets/img/papers/convdesom.png">}
}

{"_id":"49txbE6boMdbscSfb","bibbaseid":"forest-lebbah-azzag-lacaille-deeparchitecturesforjointclusteringandvisualizationwithselforganizingmaps-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":"Recent research has demonstrated how deep neural networks are able to learn representations to improve data clustering. By considering representation learning and clustering as a joint task, models learn clustering-friendly spaces and achieve superior performance, com- pared with standard two-stage approaches where dimensionality reduc- tion and clustering are performed separately. We extend this idea to topology-preserving clustering models, known as self-organizing maps (SOM). First, we present the Deep Embedded Self-Organizing Map (DE- SOM), a model composed of a fully-connected autoencoder and a custom SOM layer, where the SOM code vectors are learnt jointly with the au- toencoder weights. Then, we show that this generic architecture can be extended to image and sequence data by using convolutional and recur- rent architectures, and present variants of these models. First results demonstrate advantages of the DESOM architecture in terms of cluster- ing performance, visualization and training time.","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":"Workshop on Learning Data Representations for Clustering (LDRC), PAKDD","doi":"10.1007/978-3-030-26142-9_10","keywords":"autoencoder,clustering,deep learning,representation learning,self-organizing map","title":"Deep Architectures for Joint Clustering and Visualization with Self-Organizing Maps","year":"2019","url_link":"https://link.springer.com/chapter/10.1007/978-3-030-26142-9_10","url_paper":"LDRC-2019-DeepArchitecturesJointClusteringVisualization-full-paper.pdf","bibbase_note":"<img src=\"assets/img/papers/convdesom.png\">","bibtex":"@inproceedings{forest2019deeparchitectures,\nabstract = {Recent research has demonstrated how deep neural networks are able to learn representations to improve data clustering. By considering representation learning and clustering as a joint task, models learn clustering-friendly spaces and achieve superior performance, com- pared with standard two-stage approaches where dimensionality reduc- tion and clustering are performed separately. We extend this idea to topology-preserving clustering models, known as self-organizing maps (SOM). First, we present the Deep Embedded Self-Organizing Map (DE- SOM), a model composed of a fully-connected autoencoder and a custom SOM layer, where the SOM code vectors are learnt jointly with the au- toencoder weights. Then, we show that this generic architecture can be extended to image and sequence data by using convolutional and recur- rent architectures, and present variants of these models. First results demonstrate advantages of the DESOM architecture in terms of cluster- ing performance, visualization and training time.},\nauthor = {Forest, Florent and Lebbah, Mustapha and Azzag, Hanane and Lacaille, J{\\'{e}}r{\\^{o}}me},\nbooktitle = {Workshop on Learning Data Representations for Clustering (LDRC), PAKDD},\ndoi = {10.1007/978-3-030-26142-9_10},\nkeywords = {autoencoder,clustering,deep learning,representation learning,self-organizing map},\ntitle = {{Deep Architectures for Joint Clustering and Visualization with Self-Organizing Maps}},\nyear = {2019},\nurl_Link = {https://link.springer.com/chapter/10.1007/978-3-030-26142-9_10},\nurl_Paper = {LDRC-2019-DeepArchitecturesJointClusteringVisualization-full-paper.pdf},\nbibbase_note = {<img src=\"assets/img/papers/convdesom.png\">}\n}\n\n","author_short":["Forest, F.","Lebbah, M.","Azzag, H.","Lacaille, J."],"key":"forest2019deeparchitectures","id":"forest2019deeparchitectures","bibbaseid":"forest-lebbah-azzag-lacaille-deeparchitecturesforjointclusteringandvisualizationwithselforganizingmaps-2019","role":"author","urls":{" link":"https://link.springer.com/chapter/10.1007/978-3-030-26142-9_10"," paper":"http://florentfo.rest/files/LDRC-2019-DeepArchitecturesJointClusteringVisualization-full-paper.pdf"},"keyword":["autoencoder","clustering","deep learning","representation learning","self-organizing map"],"metadata":{"authorlinks":{"forest, f":"https://florentfo.rest/publications"}},"downloads":38},"bibtype":"inproceedings","creationDate":"2020-03-13T14:42:13.970Z","downloads":38,"keywords":["autoencoder","clustering","deep learning","representation learning","self-organizing map"],"search_terms":["deep","architectures","joint","clustering","visualization","self","organizing","maps","forest","lebbah","azzag","lacaille"],"title":"Deep Architectures for Joint Clustering and Visualization with Self-Organizing Maps","year":2019,"biburl":"http://florentfo.rest/files/publications.bib","dataSources":["pBkCjKbyeirr5jeAd","DgnR6pzJ98ZEp97PW","2puawT8ZAQyYRypA3","6rNfa4Kp6dL5sGmf5","xH8ySTsEPTLou9gyR"]}