{"679617":{"#nid":"679617","#data":{"type":"news","title":"Research Team Recognized for Improved AI Model Training Method","body":[{"value":"\u003Cp\u003EIt seems every time a phone is turned on, a software application needs an update. Many of these updates are \u0026nbsp;integrating artificial intelligence (AI) models of some sort into crucial functions of the application.\u003C\/p\u003E\u003Cp\u003EMusic retrieval apps, for example, employ AI-powered search algorithms. While an update may technically improve the app by decreasing the average error rate of music retrieval, the subtle changes to the retrieval mechanism can cause a subjective performance degradation for the user.\u003C\/p\u003E\u003Cp\u003EThis is known as software regression.\u003C\/p\u003E\u003Cp\u003EA Georgia Tech \u003Ca href=\u0022https:\/\/ece.gatech.edu\/\u0022\u003ESchool of Electrical and Computer Engineering\u003C\/a\u003E research team of postdoctoral research Fellow Mohit Prabhushankar, recent Ph.D. graduate Ryan Benkert, and Professor \u003Ca href=\u0022https:\/\/ece.gatech.edu\/directory\/ghassan-alregib\u0022\u003EGhassan AlRegib\u003C\/a\u003E were the runners-up for the Best Paper Award at the 2024 \u003Ca href=\u0022https:\/\/bigdataieee.org\/\u0022\u003EIEEE International Conference on Big Data\u003C\/a\u003E in Washington, D.C. Their research focused on minimizing subjective software regression from updates while simultaneously continuing to decrease objective errors.\u003C\/p\u003E\u003Cp\u003EThe paper, \u201cTargeting Negative Flips in Active Learning using Validation Sets,\u201d aimed to train and update AI models using the Negative Flip Rate (NFR) metric.\u003C\/p\u003E\u003Cp\u003ENFR is a measure used in machine learning to quantify the rate at which a new model makes incorrect predictions on data points that were correctly predicted by a previous model.\u003C\/p\u003E\u003Cp\u003EThe goal for the research is to have low NFR within the models with high algorithm accuracy. They were able to identify certain subsets in the training data that achieved this. The next step is creating a method that can proactively select these subsets.\u003C\/p\u003E\u003Cp\u003EThe paper ultimately proposed to construct a Regression-ordered Subset Estimation (RoSE) using the data to consistently ensure accuracy of the AI model is high while reducing NFR.\u003C\/p\u003E\u003Cp\u003EPrabhushankar received his Ph.D. in electrical engineering from Georgia Tech in 2021. He is currently a postdoctoral research fellow in the \u003Ca href=\u0022https:\/\/alregib.ece.gatech.edu\/\u0022\u003EOmni Lab for Intelligent Visual Engineering and Science\u003C\/a\u003E (OLIVES). He is working in the fields of image processing,\u003Cbr\u003Emachine learning, active learning, healthcare, and robust and explainable AI.\u003C\/p\u003E\u003Cp\u003EBenkert received his Ph.D. in electrical engineering from Georgia Tech in 2024. He is currently a deep learning software engineer at NVIDIA in Santa Clara, CA. His research interests are at the intersection of active learning, uncertainty estimation, and performance consistency in neural network learning. Prior to Georgia Tech, he received his B.Sc and M.Sc from the RWTH Aachen University in Germany.\u003C\/p\u003E\u003Cp\u003EProfessor AlRegib is currently the John and Marilu McCarty Chair Professor ECE and directs OLIVES. He and his group work on robust and interpretable machine learning algorithms, uncertainty and trust, and human in the loop algorithms. The group has demonstrated their work on a wide range of applications such as Autonomous Systems, Medical Imaging, and Subsurface Imaging. The group is interested in advancing the fundamentals as well as the deployment of such systems in real-world scenarios. He has been issued several U.S. patents and invention disclosures. He is a Fellow of the IEEE.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThe group was the runner-up for the Best Paper Award at 2024 IEEE International Conference on Big Data for their research on reducing software regression.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"The group was the runner-up for the Best Paper Award at 2024 IEEE International Conference on Big Data for their research on reducing software regression."}],"uid":"36558","created_gmt":"2025-01-15 15:41:27","changed_gmt":"2025-01-15 15:43:49","author":"zwiniecki3","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2025-01-15T00:00:00-05:00","iso_date":"2025-01-15T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"676023":{"id":"676023","type":"image","title":"Targeting Negative Flips Award.jpg","body":null,"created":"1736955701","gmt_created":"2025-01-15 15:41:41","changed":"1736955701","gmt_changed":"2025-01-15 15:41:41","alt":"Mohit Prabhushankar, Ryan Benkert, and Ghassan AlRegib","file":{"fid":"259725","name":"Targeting Negative Flips Award.jpg","image_path":"\/sites\/default\/files\/2025\/01\/15\/Targeting%20Negative%20Flips%20Award.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2025\/01\/15\/Targeting%20Negative%20Flips%20Award.jpg","mime":"image\/jpeg","size":847917,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2025\/01\/15\/Targeting%20Negative%20Flips%20Award.jpg?itok=bGmMQih3"}}},"media_ids":["676023"],"groups":[{"id":"1255","name":"School of Electrical and Computer Engineering"}],"categories":[{"id":"145","name":"Engineering"}],"keywords":[{"id":"187812","name":"artificial intelligence (AI)"},{"id":"103141","name":"Best Paper Award"},{"id":"109581","name":"deep learning"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EZachary Winiecki\u003C\/p\u003E","format":"limited_html"}],"email":["zwiniecki3@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}