BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Model extraction for clinical decision support systems - Zohreh Sh
 ams
DTSTART:20191126T130000Z
DTEND:20191126T140000Z
UID:TALK131929@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Integrating genomic\, imaging and clinical data is crucial in 
 providing more personalised diagnostic and treatment plans for cancer pati
 ents. We use a variety of machine learning methods for integrative and pre
 dictive purposes. While doing this\, we want to ensure employability in cl
 inical decision support systems by providing explanation for the recommend
 ation we make. \n\nModel extraction deals with extracting interpretable mo
 dels from uninterpretable ones\, where the former serves as the basis for 
 providing explanation in the latter. I’m going to talk about rule extrac
 tion from neural networks in a cancer data integration scenario mentioned.
  
LOCATION:SS03\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR