{"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/representation-learning-with-deconvolution","title":"Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization","arxiv_id":"1610.07258","date":"2016-10-24","proceeding":null,"authors":["Zhiguang Wang","Wei Song","Lu Liu","Fan Zhang","Junxiao Xue","Yangdong Ye","Ming Fan","Mingliang Xu"],"abstract":"We propose a new model based on the deconvolutional networks and SAX\ndiscretization to learn the representation for multivariate time series.\nDeconvolutional networks fully exploit the advantage the powerful\nexpressiveness of deep neural networks in the manner of unsupervised learning.\nWe design a network structure specifically to capture the cross-channel\ncorrelation with deconvolution, forcing the pooling operation to perform the\ndimension reduction along each position in the individual channel.\nDiscretization based on Symbolic Aggregate Approximation is applied on the\nfeature vectors to further extract the bag of features. We show how this\nrepresentation and bag of features helps on classification. A full comparison\nwith the sequence distance based approach is provided to demonstrate the\neffectiveness of our approach on the standard datasets. We further build the\nMarkov matrix from the discretized representation from the deconvolution to\nvisualize the time series as complex networks, which show more class-specific\nstatistical properties and clear structures with respect to different labels.","url_abs":"http://arxiv.org/abs/1610.07258v3","url_pdf":"http://arxiv.org/pdf/1610.07258v3.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":"representation-learning-with-deconvolution","repo_url":"https://github.com/cauchyturing/Deconv_SAX","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}