{"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/semi-unsupervised-learning-of-human-activity","title":"Semi-unsupervised Learning of Human Activity using Deep Generative Models","arxiv_id":"1810.12176","date":"2018-10-29","proceeding":null,"authors":["Matthew Willetts","Aiden Doherty","Stephen Roberts","Chris Holmes"],"abstract":"We introduce 'semi-unsupervised learning', a problem regime related to\ntransfer learning and zero-shot learning where, in the training data, some\nclasses are sparsely labelled and others entirely unlabelled. Models able to\nlearn from training data of this type are potentially of great use as many\nreal-world datasets are like this. Here we demonstrate a new deep generative\nmodel for classification in this regime. Our model, a Gaussian mixture deep\ngenerative model, demonstrates superior semi-unsupervised classification\nperformance on MNIST to model M2 from Kingma and Welling (2014). We apply the\nmodel to human accelerometer data, performing activity classification and\nstructure discovery on windows of time series data.","url_abs":"http://arxiv.org/abs/1810.12176v2","url_pdf":"http://arxiv.org/pdf/1810.12176v2.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":"semi-unsupervised-learning-of-human-activity","repo_url":"https://github.com/MatthewWilletts/GM-DGM","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":"classification","task_name":"General Classification"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"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}