BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251123T105615EST-67669Wvvbp@132.216.98.100
DTSTAMP:20251123T155615Z
DESCRIPTION:Using Machine Learning Methods to Predict Tuberculosis Treatmen
 t Resistance.\n\nMachine-learning algorithms are used to detect complex\, 
 often unforeseen patterns within rich datasets. There are two general cate
 gories of algorithms: unsupervised and supervised. Supervised machine-lear
 ning algorithms\, the topic of this presentation\, start out with a hypoth
 esis and categories that are set out in advance. These algorithms are then
  “trained” on data for which the outcomes of interest are known\, with the
  training process continuing until a desired level of accuracy is achieved
 . These results are then used to make predictions based on out-of-sample d
 ata for which the outcome of interest is not known. While most statistical
  models can be viewed as a simpler form of machine-learning algorithm that
  imposes a pre-determined functional form for the relationship between the
  predictors and the outcome of interest\, more advanced machine-learning a
 lgorithms impose much less structure and can therefore detect very complex
  and intricate relationships in high-dimensional data (i.e.\, data with se
 veral different types of variables\, possibly including quantitative\, tex
 t and image information). Advances are now being made in analyzing the out
 put of these algorithms to permit assessment of the relative importance of
  each variable. The current talk will provide an introduction to neural ne
 tworks\, an advanced supervised machine learning method. The methodology i
 s then applied to lab data from the World Health Organization (WHO) to ide
 ntify gene mutations associated with resistance to tuberculosis treatment 
 that are amenable to targeted drug therapy.\n
DTSTART:20161025T193000Z
DTEND:20161025T203000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Jimmy Royer\, Analysis Group
URL:/channels/event/jimmy-royer-analysis-group-263579
END:VEVENT
END:VCALENDAR