9/11/2019 VALSE Webinar 19-17期 脑启发视觉模型 Brain Inspired Visual Model - VALSE | 微信公众号⽂章阅读 - WeMP https://wemp.app/posts/fdffe59a-716d-440f-b92e-cf3812fc8dcd?utm_source=latest-posts 1/7 07-15 10:01:49 VALSE Webinar 19-17 Brain Inspired Visual Model VALSE 2019 7 17 20:00 Brain Inspired Visual Model Brain-inspiredIntelligence: A Paradigm for Next Generation AI University of North Carolina at Chapel Hill Neuroimage Analysis for Automated Brain Disease Diagnosis Panel 1. 2. 3. Learning for understanding brain Brain Inspired Visual Learning 4. 5. Panel University of North Carolina at Chapel Hill * panel panel VALSE valse_wechat VALSE Vision and Learning Seminar
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
报告时间:2019年7⽉17⽇(星期三)晚上20:00(北京时间)报告题⽬:Brain-inspiredIntelligence: A Paradigm for Next Generation AI
报告⼈简介:
BailuSi is a professor at the School of Systems Science of Beijing NormalUniversity. He obtained the PhD degree inTheoretical Neurophysics from BremenUniversity, Germany in 2007. During 2008-2013 he was postdoctoralresearchersin the Sector of Cognitive Neuroscience of the International School for Advanced Studies and theDepartment of Neurobiology of the Weizmann Instituteof Science, working on the computational mechanisms of theneural circuits of spatial memory. Before he joined BNU in 2018, he was a Principle Investigatorof the State KeyLaboratory of Robotics in Shenyang Institute of Automation,Chinese Academy of Sciences. His research interestincludes neural signalprocessing, brain-inspired computation and neurorobotics. He is a member in the Committeeof Computational Neuroscience and Neuroengineering of the ChineseSociety of Neuroscience, the committee ofIntelligence Interaction of the Chinese Association for Artificial Intelligence, the committee of Automation forEnvironment Perception and Protection of the Chinese Association of Automation.
个⼈主⻚:
http://www.brainair.cn
报告摘要:
Tounderstand intelligence is one of the ultimate questions for human beings.Traditional AI research is faced withchallenges such as robustness,scalability and interpretability. Brain, as the only general intelligencesystem in nature,constitutes a blueprint for AI research to understand andcreate intelligence. In this talk, I will review recent progressin neuroscienceresearch, and discuss neural network models of perception and memory. Byunderstanding thedynamics and computational mechanisms of the neural circuits,it is possible to find a path to understand and createintelligence.
参考⽂献:
[1] Dongye Zhao, Bailu Si, and Fengzhen Tang. Unsupervised feature learning for visual place recognition inchanging environments. In Proceedings of the 2019 International Joint Conference on Neural Networks. 2019.[2] Taiping Zeng and Bailu Si. Cognitive mapping based on conjunctive representations of space and movement.Frontiers in Neurorobotics, 11:61, 2017.
报告嘉宾:刘明霞(University of North Carolina at Chapel Hill)报告时间:2019年7⽉17⽇(星期三)晚上20:30(北京时间)报告题⽬:Neuroimage Analysis for Automated Brain Disease Diagnosis
报告⼈简介:
Mingxia Liu is a Research Instructor of University of North Carolina at Chapel Hill. Her research focuses on machinelearning and pattern recognition, with applications of Artificial Intelligence to studying aging and brain disorders. Herclassification method was ranked #1 in the ISBI Challenge of “Classification of Normal versus Malignant Cells in B-ALL White Blood Cancer Microscopic Images” in 2019. She is the recipient of Outstanding Doctoral DissertationNomination Award from the Chinese Association for Artificial Intelligence, Outstanding Doctoral Dissertation Awardfrom the Computer Society of Jiangsu Province, China, Travel Award of MICCAI 2016, and Travel Award of IAPR2012. She has served as the Area Chair of MICCAI 2019, Co-Chair of MLMI 2018-2019 and Co-Chair of GLMI 2019.She is a Guest Editor of Journal of Neuroscience Methods Special Issue on Deep Learning Methods andApplications in Neuroimaging, Multimedia Tools and Applications Special Issue on Multimodal Data Fusion,Learning, and Application, and Neurocomputing Special Issue on Multimodal Media Data Understanding andAnalytics. She is currently an Academic Editor for PLOS ONE.
Multi-modal neuroimages facilitate the automated diagnosis of brain disorders by providing fundamental insightsinto neurodegenerative patterns of the human brain. Nevertheless, there are still lots of challenges need to beaddressed. This talk will first present some of our recent work on brain disease analysis using structural andfunctional magnetic resonance (MR) images. We will also discuss how the heterogeneous and incomplete multi-modal neuroimaging data may benefit the automated diagnosis of brain diseases.
参考⽂献:
[1] Chunfeng Lian, Mingxia Liu, Jun Zhang, and Dinggang Shen, "Hierarchical Fully Convolutional Network for JointAtrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI," IEEE Transactions on PatternAnalysis and Machine Intelligence, DOI: 10.1109/TPAMI.2018.2889096, 2019. [2] Yongsheng Pan, Mingxia Liu*, Chunfeng Lian, Yong Xia, and Dinggang Shen. "Disease-Image Specific GenerativeAdversarial Network for Brain Disease Diagnosis with Incomplete Multi-Modal Neuroimages," In the 22ndInternational Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2019), Shenzhen, China, Oct. 13-17, 2019.
科学基⾦联合基⾦重点项⽬等多项课题,主要研究领域为⽴体视觉及脑科学,在Human Brain Mapping、MICCAI、IEEE Trans. on Medical Imaging、CVPR等国际期刊及会议发表论⽂100余篇,论⽂引⽤5000余次,由Elsevier出版英⽂专著两部。担任IEEE Trans. on Signal and Information Processing over Network及Journal of Visual Communicationand Image Representation等国际期刊编委,担任MICCAI等国际会议领域主席。
个⼈主⻚:
http://www.gaoyue.org
Panel嘉宾:胡晓林(清华⼤学)
嘉宾简介:
清华⼤学计算机系副教授。2007年在⾹港中⽂⼤学获得⾃动化与辅助⼯程专业博⼠学位,然后在清华⼤学计算机系从事博⼠后研究,2009年留校任教⾄今。他的研究领域包括⼈⼯神经⽹络和计算神经科学,主要兴趣包括开发受脑启发的计算模型和揭示⼤脑处理视听觉信息的机制,在知名国际期刊和国际会议上发表论⽂70余篇。他是IEEE Transactionson Neural Networks and Learning Systems和Cognitive Neurodynamics的编委。曾带领学⽣在各种模式识别国际竞赛中获得过6次冠军和3次亚军。
⾦、“万⼈计划”⻘年拔尖⼈才项⽬。近年来作为课题负责⼈承担国家重点研发计划、国家⾃然科学基⾦、⽜顿⾼级学者基⾦等多项课题,主要研究领域为机器学习、脑影像智能分析与脑疾病早期诊断,在TPAMI、TMI、TIP、Neuroimage、Human Brain Mapping、NIPS、MICCAI、KDD等国际期刊及会议发表论⽂100余篇,论⽂引⽤9000余次。研究成果获教育部⾃然科学⼆等奖1项(第⼀完成⼈)。担任Journal of The Franklin Institute、《⾃动化学报》等期刊编委,任中国图象图形学会理事、中国图学学会图学⼤数据专委会副主任、中国⼈⼯智能学会机器学习专委会常