{"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/co-evolutionary-multi-task-learning-for","title":"Co-evolutionary multi-task learning for dynamic time series prediction","arxiv_id":"1703.01887","date":"2017-02-27","proceeding":null,"authors":["Rohitash Chandra","Yew-Soon Ong","Chi-Keong Goh"],"abstract":"Time series prediction typically consists of a data reconstruction phase\nwhere the time series is broken into overlapping windows known as the timespan.\nThe size of the timespan can be seen as a way of determining the extent of past\ninformation required for an effective prediction. In certain applications such\nas the prediction of wind-intensity of storms and cyclones, prediction models\nneed to be dynamic in accommodating different values of the timespan. These\napplications require robust prediction as soon as the event takes place. We\nidentify a new category of problem called dynamic time series prediction that\nrequires a model to give prediction when presented with varying lengths of the\ntimespan. In this paper, we propose a co-evolutionary multi-task learning\nmethod that provides a synergy between multi-task learning and co-evolutionary\nalgorithms to address dynamic time series prediction. The method features\neffective use of building blocks of knowledge inspired by dynamic programming\nand multi-task learning. It enables neural networks to retain modularity during\ntraining for making a decision in situations even when certain inputs are\nmissing. The effectiveness of the method is demonstrated using one-step-ahead\nchaotic time series and tropical cyclone wind-intensity prediction.","url_abs":"http://arxiv.org/abs/1703.01887v2","url_pdf":"http://arxiv.org/pdf/1703.01887v2.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":"co-evolutionary-multi-task-learning-for","repo_url":"https://github.com/rohitash-chandra/CMTL_dynamictimeseries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"evolutionary-algorithms","task_name":"Evolutionary Algorithms"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-prediction","task_name":"Time Series Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}