{"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/bidirectional-deep-readout-echo-state","title":"Bidirectional deep-readout echo state networks","arxiv_id":"1711.06509","date":"2017-11-17","proceeding":null,"authors":["Filippo Maria Bianchi","Simone Scardapane","Sigurd Løkse","Robert Jenssen"],"abstract":"We propose a deep architecture for the classification of multivariate time\nseries. By means of a recurrent and untrained reservoir we generate a vectorial\nrepresentation that embeds temporal relationships in the data. To improve the\nmemorization capability, we implement a bidirectional reservoir, whose last\nstate captures also past dependencies in the input. We apply dimensionality\nreduction to the final reservoir states to obtain compressed fixed size\nrepresentations of the time series. These are subsequently fed into a deep\nfeedforward network trained to perform the final classification. We test our\narchitecture on benchmark datasets and on a real-world use-case of blood\nsamples classification. Results show that our method performs better than a\nstandard echo state network and, at the same time, achieves results comparable\nto a fully-trained recurrent network, but with a faster training.","url_abs":"http://arxiv.org/abs/1711.06509v3","url_pdf":"http://arxiv.org/pdf/1711.06509v3.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":"bidirectional-deep-readout-echo-state","repo_url":"https://github.com/FilippoMB/Bidirectional-Deep-Echo-State-Network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"bidirectional-deep-readout-echo-state","repo_url":"https://github.com/FilippoMB/Bidirectional-Deep-reservoir-Echo-State-Network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}