- My office phone will not work, after 1/Aug/2015.
Use email, or if very timely, contact our Admin at 780 492-4828.
- If you want to take the Introduction to Machine Learning course
(Cmput466 for ugrads; Cmput551 for grads) this fall,
please see the short
which includes the "Required Background".
- To understand the difference between
Association Studies (common in biostatistics)
Prediction Studies (common in machine learning),
Our fMRI project is included as an example of UofA's collaboration with IBM
in news release.
- Our team, led by PhD student Siamak Ravansbakhsh, developed the
for automatically identifying and quantifying metabolites using 1D 1H NMR spectra of
ultra-filtered plasma, serum or cerebrospinal fluid.
Our article is described on
and elsewhere (May,June 2015).
We are proud to be part of the
that is developing a tool to help patients manage their Type I diabetes --
which was described on GlobalTV on Thurs 14/May
U of A app to manage diabetes.
- PhD student Siamak Ravansbakhsh won a Best Thesis Prize (2015)
- PhD student Felicity Allen's CFM-ID system won the
CASMI [Critical Assessment of Small Molecule Identification]
competition (finding the structure, of a MS/MS spectrum)
- Press coverage of MITACS
- Press coverage of Accurately Predicting Estrogen Receptor Status
and H. Khosravi,
The IMAP Hybrid Method for Learning Gaussian Bayes Nets"
Best Paper Prize
2010 Canadian Conference on Artificial Intelligence.
Annual Professorship, 2007.
- Fellow of
(Association for the Advancement of
Artificial Intelligence), 2007
- Faculty Research Award, UofA CS (March 2007)
(to AICML) for
"Outstanding Leadership in Technology",
Int'l Conf. on Machine Learning (ICML'06)
Learning Coordinate Classifiers"
"Distinguished Paper" award
Int'l Conf. on Machine Learning (ICML'04)
"Learning a Model of a Web User's Interests"
2003 James Chen Best
Student Paper Award at
- J.Cheng and R. Greiner,
"Learning Bayesian Belief Network Classifiers: Algorithms and System"
was RunnerUp for Best Paper,
Fourteenth Canadian Conference on Artificial Intelligence (CSCSI'01)
I am interested in building algorithms that learn from experience, to be able to
perform their tasks better.
Some of my work has
These systems have been successfully used to address
a number of real-world challenges.
- an application pull
-- i.e., is motivated by very specific tasks;
a technology push -- typically extending standard learning algorithms and analyses, to produce more robust and more effective learning systems
For an overview of some medical application for machine learning, see the
Thought for the day:
First things first; second things never.
I plan to update this daily... but that is not the highest