{"675438":{"#nid":"675438","#data":{"type":"news","title":"Hybrid Machine Learning Model Untangles Web of Communication in the Brain","body":[{"value":"\u003Cp\u003EA new machine learning (ML) model created at Georgia Tech is helping neuroscientists better understand communications between brain regions. Insights from the model could lead to personalized medicine, better brain-computer interfaces, and advances in neurotechnology.\u003C\/p\u003E\u003Cp\u003EThe Georgia Tech group combined two current ML methods into their hybrid model called MRM-GP (Multi-Region Markovian Gaussian Process).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENeuroscientists who use MRM-GP learn more about communications and interactions within the brain. This in turn improves understanding of brain functions and disorders.\u003C\/p\u003E\u003Cp\u003E\u201cClinically, MRM-GP could enhance diagnostic tools and treatment monitoring by identifying and analyzing neural activity patterns linked to various brain disorders,\u201d said \u003Ca href=\u0022https:\/\/scholar.google.com\/citations?user=qW4_NR4AAAAJ\u0026amp;hl=en\u0022\u003EWeihan Li\u003C\/a\u003E, the study\u2019s lead researcher.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cNeuroscientists can leverage MRM-GP for its robust modeling capabilities and efficiency in handling large-scale brain data.\u201d\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMRM-GP reveals where and how communication travels across brain regions.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe group tested MRM-GP using spike trains and local field potential recordings, two kinds of measurements of brain activity. These tests produced representations that illustrated directional flow of communication among brain regions.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EExperiments also disentangled brainwaves, called oscillatory interactions, into organized frequency bands. MRM-GP\u2019s hybrid configuration allows it to model frequencies and phase delays within the latent space of neural recordings.\u003C\/p\u003E\u003Cp\u003EMRM-GP combines the strengths of two existing methods: the Gaussian process (GP) and linear dynamical systems (LDS). The researchers say that MRM-GP is essentially an LDS that mirrors a GP.\u003C\/p\u003E\u003Cp\u003ELDS is a computationally efficient and cost-effective method, but it lacks the power to produce representations of the brain. GP-based approaches boost LDS\u0027s power, facilitating the discovery of variables in frequency bands and communication directions in the brain.\u003C\/p\u003E\u003Cp\u003EConverting GP outputs into an LDS is a difficult task in ML. The group overcame this challenge by instilling separability in the model\u2019s multi-region kernel. Separability establishes a connection between the kernel and LDS while modeling communication between brain regions.\u003C\/p\u003E\u003Cp\u003EThrough this approach, MRM-GP overcomes two challenges facing both neuroscience and ML fields. The model helps solve the mystery of intraregional brain communication. It does so by bridging a gap between GP and LDS, a feat not previously accomplished in ML.\u003C\/p\u003E\u003Cp\u003E\u201cThe introduction of MRM-GP provides a useful tool to model and understand complex brain region communications,\u201d said Li, a Ph.D. student in the School of Computational Science and Engineering (CSE).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cThis marks a significant advancement in both neuroscience and machine learning.\u201d\u003C\/p\u003E\u003Cp\u003EFellow doctoral students\u0026nbsp;\u003Ca href=\u0022https:\/\/github.com\/JerrySoybean\u0022\u003EChengrui Li\u003C\/a\u003E and\u0026nbsp;\u003Ca href=\u0022https:\/\/github.com\/yulewang97\u0022\u003EYule Wang\u003C\/a\u003E co-authored the paper with Li. School of CSE Assistant Professor\u0026nbsp;\u003Ca href=\u0022https:\/\/sites.google.com\/site\/anqiwuresearch\u0022\u003EAnqi Wu\u003C\/a\u003E advises the group.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EEach MRM-GP student pursues a different\u0026nbsp;\u003Ca href=\u0022https:\/\/cse.gatech.edu\/phd-programs\u0022\u003EPh.D. degree offered by the School of CSE\u003C\/a\u003E. W. Li studies computer science, C. Li studies computational science and engineering, and Wang studies machine learning. The school also offers Ph.D. degrees in bioinformatics and bioengineering.\u003C\/p\u003E\u003Cp\u003EWu is a 2023 recipient of the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/news\/anqi-wu-awarded-2023-sloan-research-fellowship\u0022\u003ESloan Research Fellowship\u003C\/a\u003E for neuroscience research. Her work straddles two of the\u0026nbsp;\u003Ca href=\u0022https:\/\/cse.gatech.edu\/research\u0022\u003ESchool\u2019s five research areas\u003C\/a\u003E: machine learning and computational bioscience.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EMRM-GP will be featured at the world\u2019s top conference on ML and artificial intelligence. The group will share their work at the International Conference on Machine Learning (\u003Ca href=\u0022https:\/\/icml.cc\/\u0022\u003EICML 2024\u003C\/a\u003E), which will be held July 21-27 in Vienna.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EICML 2024 also accepted for presentation a second paper from Wu\u2019s group intersecting neuroscience and ML. The same authors will present\u0026nbsp;\u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2402.01263\u0022\u003E\u003Cem\u003EA Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing\u003C\/em\u003E\u003C\/a\u003E.\u003C\/p\u003E\u003Cp\u003ETwenty-four Georgia Tech faculty from the Colleges of Computing and Engineering will present 40 papers at ICML 2024. Wu is one of six faculty representing the School of CSE who will present eight total papers.\u003C\/p\u003E\u003Cp\u003EThe group\u2019s ICML 2024 presentations exemplify Georgia Tech\u2019s focus on neuroscience research as a\u0026nbsp;\u003Ca href=\u0022https:\/\/research.gatech.edu\/strategic-initiatives\u0022\u003Estrategic initiative\u003C\/a\u003E. \u0026nbsp;\u003C\/p\u003E\u003Cp\u003EWu is an affiliated faculty member with the\u0026nbsp;\u003Ca href=\u0022https:\/\/www.gatech.edu\/news\/2023\/09\/18\/georgia-tech-launch-interdisciplinary-neurosciences-research-program\u0022\u003ENeuro Next Initiative\u003C\/a\u003E, a new interdisciplinary program at Georgia Tech that will lead research in neuroscience, neurotechnology, and society. The University System of Georgia Board of Regents recently approved a new\u0026nbsp;\u003Ca href=\u0022https:\/\/news.gatech.edu\/news\/2024\/05\/02\/georgia-tech-offer-phd-neuroscience-and-neurotechnology-new-minor\u0022\u003Eneuroscience and neurotechnology Ph.D. program\u003C\/a\u003E at Georgia Tech.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cPresenting papers at international conferences like ICML is crucial for our group to gain recognition and visibility, facilitates networking with other researchers and industry professionals, and offers valuable feedback for improving our work,\u201d Wu said.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u201cIt allows us to share our findings, stay updated on the latest developments in the field, and enhance our professional development and public speaking skills.\u201d\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EVisit \u003C\/em\u003E\u003Ca href=\u0022https:\/\/sites.gatech.edu\/research\/icml-2024\/\u0022\u003E\u003Cem\u003Ehttps:\/\/sites.gatech.edu\/research\/icml-2024\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E for news and coverage of Georgia Tech research presented at ICML 2024.\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EA new machine learning (ML) model created at Georgia Tech is helping neuroscientists better understand communications between brain regions. Insights from the model could lead to personalized medicine, better brain-computer interfaces, and advances in neurotechnology.\u003C\/p\u003E\u003Cp\u003EThe Georgia Tech group combined two current ML methods into their hybrid model called MRM-GP (Multi-Region Markovian Gaussian Process).\u0026nbsp;\u003C\/p\u003E\u003Cp\u003ENeuroscientists who use MRM-GP learn more about communications and interactions within the brain. This in turn improves understanding of brain functions and disorders.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"A new machine learning (ML) model created at Georgia Tech is helping neuroscientists better understand communications between brain regions. "}],"uid":"36319","created_gmt":"2024-07-11 19:37:12","changed_gmt":"2024-07-12 15:25:01","author":"Bryant Wine","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2024-07-11T00:00:00-04:00","iso_date":"2024-07-11T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"674337":{"id":"674337","type":"image","title":"MRM-GP Head Photo.jpg","body":null,"created":"1720726656","gmt_created":"2024-07-11 19:37:36","changed":"1720726656","gmt_changed":"2024-07-11 19:37:36","alt":"Weihan Li ICML 2024","file":{"fid":"257837","name":"MRM-GP Head Photo.jpg","image_path":"\/sites\/default\/files\/2024\/07\/11\/MRM-GP%20Head%20Photo.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/MRM-GP%20Head%20Photo.jpg","mime":"image\/jpeg","size":92978,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/MRM-GP%20Head%20Photo.jpg?itok=CyGJUal2"}},"674338":{"id":"674338","type":"image","title":"YW Poster.jpg","body":null,"created":"1720726696","gmt_created":"2024-07-11 19:38:16","changed":"1720726696","gmt_changed":"2024-07-11 19:38:16","alt":"Yule Wang ICML 2024 CSE","file":{"fid":"257838","name":"YW Poster.jpg","image_path":"\/sites\/default\/files\/2024\/07\/11\/YW%20Poster.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/YW%20Poster.jpg","mime":"image\/jpeg","size":37723,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/YW%20Poster.jpg?itok=nnjhmwZN"}},"674339":{"id":"674339","type":"image","title":"CSE_ICML2024.png","body":null,"created":"1720726742","gmt_created":"2024-07-11 19:39:02","changed":"1720726742","gmt_changed":"2024-07-11 19:39:02","alt":"CSE ICML 2024","file":{"fid":"257839","name":"CSE_ICML2024.png","image_path":"\/sites\/default\/files\/2024\/07\/11\/CSE_ICML2024.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/07\/11\/CSE_ICML2024.png","mime":"image\/png","size":173722,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/07\/11\/CSE_ICML2024.png?itok=uiGRsZ3_"}}},"media_ids":["674337","674338","674339"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1188","name":"Research Horizons"},{"id":"50877","name":"School of Computational Science and Engineering"}],"categories":[{"id":"138","name":"Biotechnology, Health, Bioengineering, Genetics"},{"id":"153","name":"Computer Science\/Information Technology and Security"},{"id":"135","name":"Research"},{"id":"134","name":"Student and Faculty"},{"id":"8862","name":"Student Research"}],"keywords":[{"id":"192863","name":"go-ai"},{"id":"10199","name":"Daily Digest"},{"id":"9153","name":"Research Horizons"},{"id":"172970","name":"go-neuro"},{"id":"187915","name":"go-researchnews"}],"core_research_areas":[{"id":"193656","name":"Neuro Next Initiative"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBryant Wine, Communications Officer\u003Cbr\u003E\u003Ca href=\u0022mailto:bryant.wine@cc.gatech.edu\u0022\u003Ebryant.wine@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}