BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Collecting\, Modeling and Predicting Biomedical Measurements in th
 e Age of Machine Learning
DTSTART:20180131T101500
DTSTAMP:20260509T103421Z
UID:95bf525b2039d3ed36e1452ee1f6e99b488124b010f3687b5e2f0948
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Łukasz Kidziński from the Mobilize Center at Stanford Un
 iversity\nAbstract\nRecent achievements in machine learning are subverting
  foundations of many research disciplines. In this presentation\, I will s
 how how these developments affect collection\, modeling and prediction of 
 human gait kinematics\, enabling unprecedented scale of research and appli
 cations. I will focus on our novel technique for predicting progression tr
 ajectories of pathologic gait kinematics from sparse observations\, using 
 matrix completion techniques. I will present how we can collect these kine
 matic data with equipment 100x cheaper than usual and how we model kinemat
 ics using reinforcement learning\, leveraging large computational resource
 s and domain knowledge embedded in simulation software.\n \nBiography\nŁ
 ukasz Kidziński is a researcher in the Mobilize Center at Stanford Univer
 sity\, working on the intersection of computer science\, statistics and bi
 omechanics. Previously a data scientist in the CHILI group\, Computer-Huma
 n Interaction in Learning and Instruction\, at the EPFL.\nHis main interes
 ts include computational methods in biomedical data\, including applicatio
 ns of machine learning\, data mining\, big data\, time series analysis and
  statistics.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR