[Solomonov Seminar] 235. Solomonov seminar

[Marko Grobelnik]

V torek 27.9. ob 13:00 bo v Veliki predavalnici IJS
(prvo nadstropje glavne stavbe IJS) 235. Solomonov seminar.

Predaval bo William Klement na temo ROC krivulj, popularne
tehnike vrednotenja modelov v strojnem ucenju.

Posnetki preteklih seminarjev so na http://videolectures.net/solomon/


~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~`

William Klement, University of Ottawa, Canada:
          Smooth Receiver Operating Characteristics Curves (smROC)

Supervised learning algorithms perform common tasks including
classification, ranking, scoring, and probability estimation. We
investigate how scoring information, often produced by these models, is
utilized by an evaluation measure. The ROC curve represents a visualization
of the ranking performance of classifiers. However, they ignore the
scores which can be quite informative. While this ignored information
is less precise than that given by probabilities, it is much more detailed
than that conveyed by ranking. This paper presents a novel method
to weight the ROC curve by these scores. We call it the Smooth ROC
(smROC) curve, and we demonstrate how it can be used to visualize
the performance of learning models. We report experimental results to
show that the smROC is appropriate for measuring performance similarities
and differences between learning models, and is more sensitive to
performance characteristics than the standard ROC curve.

A Short Bio.:
William Klement earned his Ph.D. in Computer science at the University 
of Ottawa in the area of evaluation of machine learning algorithms. 
After receiving his Ph.D., Mr. Klement joined the department of 
Pathology, Anatomy & Cell Biology at Jefferson Medical College in 
Pennsylvania, USA, where he investigated the identification and the 
quality assessment of microRNA target sites on the human genome. In 
addition to pursuing his Ph.D., he was a member of the MET Research 
Group at the university of Ottawa, Canada. He conducted research on 
selecting machine learning methods appropriate for predicting patients' 
outcomes in the Emergency Department. Prior to pursuing his Ph.D., Mr. 
Klement has held several teaching positions as a faculty lecturer at the 
University of Alberta, as well as, the University of Guelph. His 
research interests are focused on evaluating machine learning algorithms 
in medical domains, and in particular, studying the relationship between 
classification and ranking.