{"681662":{"#nid":"681662","#data":{"type":"event","title":"PhD Defense by Cameron Taylor","body":[{"value":"\u003Cp\u003ETitle: Online Unsupervised Continual Learning for Agents in Online and Dynamic Environments\u003C\/p\u003E\u003Cp\u003EDate: Wednesday, April 16th\u003Cbr\u003ETime: 4:00-5:30 PM EST\u003Cbr\u003ELocation: Coda C1115 Druid Hills (zoom)\u003C\/p\u003E\u003Cp\u003ECameron Ethan Taylor\u003Cbr\u003EMachine Learning PhD Student\u003Cbr\u003ESchool of Interactive Computing\u003Cbr\u003EGeorgia Institute of Technology\u003C\/p\u003E\u003Cp\u003ECommittee\u003Cbr\u003E1 Dr. Constantine Dovrolis (Advisor), School of Computer Science, Georgia Tech\u003Cbr\u003E2 Dr. Zsolt Kira, School of Interactive Computing, Georgia Tech\u003Cbr\u003E3 Dr. Yingyan (Celine) Lin, School of Computer Science, Georgia Tech\u003Cbr\u003E4 Dr. Alexey Tumanov, School of Computer Science, Georgia Tech\u003Cbr\u003E5 Dr. Osama Alshaykh, College of Engineering, Boston University\u003C\/p\u003E\u003Cp\u003EAbstract\u003C\/p\u003E\u003Cp\u003EDeep learning systems have demonstrated remarkable capabilities in learning useful representations from complex data. However, these capabilities typically rely on assumptions that the training data is fully available in advance, that some or all of it is labeled, and that its distribution is fixed and matches future test data. These assumptions stand in stark contrast to the conditions under which biological learners\u2014such as humans or animals\u2014learn from their environments. To bridge this gap, this dissertation introduces Online Unsupervised Continual Learning (O-UCL), a new learning setting where data arrives as an unlabeled, non-stationary stream. The thesis first formalizes the O-UCL problem and presents an initial solution inspired by neuroscience and classical machine learning. It then introduces a second approach that leverages contrastive learning to handle more challenging natural image streams. Finally, it explores additional challenges unique to O-UCL and outlines the properties necessary for robust, adaptive solutions to those challenges. This work lays a foundation for the development of learning algorithms that can operate in complex, ever-changing real-world environments.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EOnline Unsupervised Continual Learning for Agents in Online and Dynamic Environments\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Online Unsupervised Continual Learning for Agents in Online and Dynamic Environments"}],"uid":"27707","created_gmt":"2025-04-08 15:56:41","changed_gmt":"2025-04-08 15:57:08","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-04-16T16:00:00-04:00","event_time_end":"2025-04-16T17:30:00-04:00","event_time_end_last":"2025-04-16T17:30:00-04:00","gmt_time_start":"2025-04-16 20:00:00","gmt_time_end":"2025-04-16 21:30:00","gmt_time_end_last":"2025-04-16 21:30:00","rrule":null,"timezone":"America\/New_York"},"location":"Coda C1115 Druid Hills (zoom)","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}