BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Michigan Institute for Computational Discovery and Engineering - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Michigan Institute for Computational Discovery and Engineering
X-ORIGINAL-URL:https://micde.umich.edu
X-WR-CALDESC:Events for Michigan Institute for Computational Discovery and Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20180311T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20181104T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20201002T090000
DTEND;TZID=America/Detroit:20201002T100000
DTSTAMP:20230905T171254Z
CREATED:20230905T171254Z
LAST-MODIFIED:20230905T171254Z
UID:10000422-1601629200-1601632800@micde.umich.edu
SUMMARY:Neuroimaging Initiative webinar: Bayesian scalar-on-image neural networks with application to neuroimaging data
DESCRIPTION:About Dr. Kang: Jian Kang is a Professor in the Department of Biostatistics and is a faculty member of the Kidney Epidemiology and Cost Center (KECC) at the University of Michigan.  He received his PhD in Biostatistics from the University of Michigan in 2011. He was an Assistant Professor in the Department of Biostatistics and Bioinformatics and the Department of Radiology and Imaging Sciences at Emory University from 2011 – 2015. He was a core faculty member in the Center for Biomedical Imaging Statistics (CBIS) at Emory University.  His primary research interests are in developing statistical methods for large-scale complex biomedical data with application in precision medicine\, imaging\, epidemiology and genetics. \n\nBAYESIAN SCALAR-ON-IMAGE NEURAL NETWORKS WITH APPLICATION TO NEUROIMAGING DATA\nDeep neural networks have been adopted in the scalar-on-image regression which predicts the outcome variable using image predictors. However\, training DNN often requires a large sample size to achieve a good prediction accuracy and the model fitting results can be difficult to interpret. In this work\, we construct a novel single-layer Bayesian neural network (BNN) with spatially-varying coefficients (SVC) for the scalar-on-image regression. Our goal is to select interpretable image features and to achieve the high prediction accuracy with limited training samples. We assign the soft-thresholded Gaussian process (STGP) prior to the SVCs and develop an efficient posterior computation algorithm based on stochastic gradient Langevin Dynamics (SGLD). The BNN-STGP provides a large prior support for sparse\, piecewise-smooth and continuous SVCs\, enabling efficient posterior inference on image feature selection and automatically determining the network structures. We establish the posterior consistency of estimating the SVCs in the model and image feature selection consistency when the number of voxels/pixels grows much faster than the sample size. We compared our methods with state-of-the-art deep learning methods via extensive simulations and analyses of multiple real datasets including the task fMRI data from the ABCD study. \n\nConnect to the webinar via this link. Meeting ID: 923 3875 2870. Meeting Passcode: 149254
URL:https://micde.umich.edu/event/bayesian-scalar-on-image-neural-networks-with-application-to-neuroimaging-data/
LOCATION:Zoom Event
CATEGORIES:Webinar
ATTACH;FMTTYPE=image/jpeg:https://micde.umich.edu/wp-content/uploads/2023/02/Jian-Kang-Headshot.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20190218T150000
DTEND;TZID=America/Detroit:20190218T160000
DTSTAMP:20230905T171358Z
CREATED:20230905T171358Z
LAST-MODIFIED:20230905T171358Z
UID:10000207-1550502000-1550505600@micde.umich.edu
SUMMARY:MICDE Seminar: Jim Haxby\, Evans Family Distinguished Professor; Director\, Center for Cognitive Neuroscience\, Dartmouth College
DESCRIPTION:Bio1: James V. Haxby is a professor in the Department of Psychological and Brain Sciences at Dartmouth College and the Director for the Dartmouth Center for Cognitive Neuroscience. He is best known for his work on face perception and applications of machine learning in functional neuroimaging. Haxby received a BA from Carleton College in 1973 and completed a Fulbright Scholarship at the University of Bonn in 1974. He obtained a PhD in clinical psychology at the University of Minnesota in 1981. After receiving his PhD\, Haxby held several clinical psychology positions at the Minneapolis VA Medical Center. Starting in 1982\, Haxby began a two-decade tenure at the National Institutes of Health\, working as a research psychologist at the National Institute on Aging and later as chief of the Section on Functional Brain Imaging at the National Institute of Mental Health. In 2002\, Haxby began a professorship in the Department of Psychology at Princeton University\, and in 2008 became the Evans Family Distinguished Professor of Psychological and Brain Sciences at Dartmouth College. \nHaxby’s scientific contributions span several topics in cognitive neuroscience. He has published numerous papers using functional neuroimaging to investigate the cortical organization underlying visual perception and semantic memory.He has also proposed an influential model of face perception where certain brain areas process invariant face properties such identity\, while others process dynamic features critical for social interaction\, such as emotional expressions and eye gaze. Haxby has played a critical role in introducing machine learning methods to functional magnetic resonance imaging (fMRI) data analysis. This approach was popularized by a paper demonstrating that neural representations of faces and object categories are encoded in a distributed fashion in human ventral temporal cortex\, a position that is typically contrasted with more modular accounts of the functional neuroanatomy of face processing. \n[1] https://en.wikipedia.org/wiki/James_V._Haxby \nBRIDGING THE DIVIDE: FOSTERING INTERDISCIPLINARY COLLABORATIVE RESEARCH IN COMPUTATIONAL COGNITIVE NEUROSCIENCE\nComputational cognitive neuroscience is a burgeoning field. Sensitive imaging methods can now measure changing patterns of brain activity noninvasively producing massive\, rich datasets. With open neuroscience\, vast amounts of functional brain imaging data are publicly available. Advances in computational methods for analyzing these data and modeling the underlying cognitive processes have produced a host of sophisticated algorithms that produce surprising new insights\, and these algorithms are available in extensive repositories of open source code. Building the interdisciplinary community for this type of collaborative research\, however\, presents challenges. Taking advantage of these resources requires integration of knowledge of cognitive neuroscience to direct projects to important questions and knowledge of rapidly evolving computational approaches that can tackle these questions in innovative ways. Building an interdisciplinary community will involve developing both productive interdisciplinary collaborative teams and a new breed of “bilingual” computational cognitive neuroscientist. \nProf. Haxby is being hosted my MICDE and the Michigan Neuroimaging Initiative. If you would like to meet Prof. Haxby\, please send an email to micde-events@umich.edu. If you are an MICDE\, MIDAS or Neuroscience student or postdoc and would like to join him for lunch\, please RSVP here (space is limited\, first-come\, first-serve)
URL:https://micde.umich.edu/event/micde-seminar-jim-haxby-evans-family-distinguished-professor-director-center-for-cognitive-neuroscience-dartmouth-college/
LOCATION:1017 H. H. Dow\, 2300 Hayward St.\, Ann Arbor\, MI\, 48109\, United States
CATEGORIES:Featured Events,MICDE Seminar Series
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2019/02/James-V.-Haxby.png
END:VEVENT
END:VCALENDAR