{"type":"ScholarlyArticle","title":"Online Deep Learning: Learning Deep Neural Networks on the Fly","authors":[{"name":"Doyen Sahoo","slug":"doyen-sahoo","given":"Doyen","family":"Sahoo","affiliation":""},{"name":"Quang Pham","slug":"quang-pham","given":"Quang","family":"Pham","affiliation":""},{"name":"Jing Lu","slug":"jing-lu","given":"Jing","family":"Lu","affiliation":""},{"name":"Steven C. H. Hoi","slug":"steven-c-h-hoi","given":"Steven C. H.","family":"Hoi","affiliation":""}],"abstract":"Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch setting, requiring the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream. We aim to address an open challenge of ``Online Deep Learning\" (ODL) for learning DNNs on the fly in an online setting. Unlike traditional online learning that often optimizes some convex objective function with respect to a shallow model (e.g., a linear/kernel-based hypothesis), ODL is more challenging as the optimization objective is non-convex, and regular DNN with standard backpropagation does not work well in practice for online settings. We present a new ODL framework that attempts to tackle the challenges by learning DNN models which dynamically adapt depth from a sequence of training data in an online learning setting. Specifically, we propose a novel Hedge Backpropagation (HBP) method for online updating the parameters of DNN effectively, and validate the efficacy on large data sets (both stationary and concept drifting scenarios).","doi":"10.24963/ijcai.2018/369","url":"https://ijcai.org/proceedings/2018/369","pdf":"https://ijcai.org/proceedings/2018/0369.pdf","markdown":"https://ijcai.org/proceedings/2018/369.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/369","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":369,"pages":{"first":2660,"last":2666},"keywords":["Machine Learning: Online Learning","Machine Learning: Time-series;Data Streams","Machine Learning: Neural Networks","Machine Learning: Deep Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}