BEGIN:VCALENDAR
VERSION:2.0
PRODID:talks.ox.ac.uk
BEGIN:VEVENT
SUMMARY:Multivariate Machine Learning Techniques for Data Preprocessing\, 
 Decomposition\, and Integration: Radiomics\, Sparse Partial Least Squares\
 , and Transformers - Dr David Popovic (Max Planck Institute of Psychiatry)
DTSTART;VALUE=DATE-TIME:20250429T093000
DTEND;VALUE=DATE-TIME:20250429T103000
UID:https://new.talks.ox.ac.uk/talks/id/67c2e6bc-0e60-43fb-ba4d-16a705ed72
 93/
DESCRIPTION:In this talk\, different machine learning techniques will be i
 ntroduced that may help neuroscientific researchers in multiple ways rangi
 ng from data preprocessing to decomposition or integration. The focus will
  be the Sparse Partial Least Squares (SPLS) algorithm as well as its exten
 sion\, the multi-block SPLS (mbSPLS). It will be shown how SPLS and mbSPLS
  can extract various layers of multivariate effects between any combinatio
 n of two or more data matrices. Investigations into neuroinflammation-brai
 n patterns as well as deeply layered genetic-brain-behavior signatures in 
 the early-age PRONIA cohort will be given as specific examples. Furthermor
 e\, forays into hostility and neurodestructive processes in early and late
 -stage psychosis will be presented.\nA smaller part of the talk will revol
 ve around novel approaches that go beyond data analysis. Specifically\, a 
 brief introduction to radiomics will highlight the potential for machine l
 earning techniques in extracting new and innovative features from MRI scan
 s\, such as texture\, entropy\, and contrast. Moreover\, transformer-based
  pipelines will be shown that allow the researcher to integrate multiple d
 ata domains from different cohorts to answer specific research questions w
 ithout any requirement for data or sample homogenization. \nOverall\, the 
 talk will cover the fundamentals of these techniques\, however\, the focus
  will be on the application and translational value of these approaches\n\
 nThis talk is hosted online only. To join\, please use the link below:\nzo
 om.us/j/92620728590?pwd=s1JefrGff6bN0nZZcHSTBkCw8Z1RlT.1\nMeeting ID: 926 
 2072 8590\nPasscode: 196542\nSpeakers:\nDr David Popovic (Max Planck Insti
 tute of Psychiatry)
LOCATION:Department of Psychiatry (Online only\, via Zoom )\, Headington O
 X3 7JX
TZID:Europe/London
URL:https://new.talks.ox.ac.uk/talks/id/67c2e6bc-0e60-43fb-ba4d-16a705ed72
 93/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Multivariate Machine Learning Techniques for Data Preproc
 essing\, Decomposition\, and Integration: Radiomics\, Sparse Partial Least
  Squares\, and Transformers - Dr David Popovic (Max Planck Institute of Ps
 ychiatry)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR