{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-neural-maps","title":"Deep Neural Maps","arxiv_id":"1810.07291","date":"2018-10-16","proceeding":null,"authors":["Mehran Pesteie","Purang Abolmaesumi","Robert Rohling"],"abstract":"We introduce a new unsupervised representation learning and visualization\nusing deep convolutional networks and self organizing maps called Deep Neural\nMaps (DNM). DNM jointly learns an embedding of the input data and a mapping\nfrom the embedding space to a two-dimensional lattice. We compare\nvisualizations of DNM with those of t-SNE and LLE on the MNIST and COIL-20 data\nsets. Our experiments show that the DNM can learn efficient representations of\nthe input data, which reflects characteristics of each class. This is shown via\nback-projecting the neurons of the map on the data space.","url_abs":"http://arxiv.org/abs/1810.07291v1","url_pdf":"http://arxiv.org/pdf/1810.07291v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-neural-maps","repo_url":"https://github.com/aishikhar/DNM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}