Russell Greiner

Positions for PostDoctoral Fellows

We are looking to hire strong researchers as postdoctoral fellows (PDFs), for various projects -- both application pull and technology push. These positions are all associated with the Alberta Ingenuity Centre for Machine Learning. -- see our ad.

If you are interested in any of the positions mentioned below, please send me ...

  • a cover letter, specifying which positions most interest you and indicating why you feel you qualify;
  • your academic transcript;
  • your CV, including a description of any previous research or industrial jobs you have held; and
  • a list of your references, preferably including their email addresses.

Russell Greiner
359 Athabasca
Phone: (780) 492-5461

We may have some funding for the first three positions; in general, it is helpful if you have funding to bring in (part of) your salary from some external sources (eg, a PostDoctoral Fellowship).


Patient-specific Cancer Treatment (PolyomX) (pdf)

Learn which treatment should be most effective for each specific (cancer) patient, based on
  • Genetic data -- SNP (single nucleotide polyomorphism) profiles
  • Proteomic data -- microarrays (showing gene expression levels)
  • Metabolomic data -- eg, NMR urinalysis

In collaboration with Medical Researchers (cancer genomics) at the Cross Cancer Institute.
Project webpage: PolyomX Project

Brain Tumor Analysis Project

GOAL#1: Segmentation -- find location of brain tumour
  • Design algorithms for using Magnetic Resonance Images (T1/T2/T1c/FLAIR/MPRAGE/...) data to find locations of tumours
    Perhaps using Random Fields (eg, CRF, DRF, or SVRFs), or level sets, or combinations
  • Perhaps incorporate other modalities -- DTI, PET, fMRI, ...

  • Find other anatomical features in (MR) Images -- eg, eyes, brainstems, ...
GOAL#2: Predict location of "radiologically occult" tumour volumes
  • Design algorithms for using current information to predict tumour growth
  • Explore other modalities -- DTI, PET, ...
In collaboration with Radiation Oncologists at the Cross Cancer Institute.
Project Webpage

This work may later extend to other medical imaging tasks, perhaps with Ross Mitchell, and Calgary Scientific; see also Imaging Informatics


Bovine Haplotype Project (AFNS)

This project involves developing genomic selection methods and tools for beef cattle -- eg, analysing SNP (single nucleotide polyomorphism) profiles of cattles, to help estimate "breeding value". This is with members of the Department of Agricultural, Food and Nutritional Science (AFNS).


Proteome Analyst

The Proteome Analyst system can analyse a set of peptide sequences (proteins) in a given proteome and return the general function, and subcellular location, of each protein, as well as a functional summary for the entire proteome. The current version first maps each novel protein to a set of attributes -- namely the tokens that appear in certain fields of the (known proteins) homologs found by Blast -- then finds the general function (resp., subcellular location) most associated with this token-set, based on a learned classifier. We are looking for a researcher (summer student, grad student, postdoctoral fellow) to help us extend Protein Analysis in several ways:

  • to take a genome as input (rather than a proteome),
  • to use other information in the classification, including the secondary structure of possible homologs, as well as information about the other sequences given in the proteome
  • to use more sophisticated learning algorithms, (including "mixture" methods to combine multiple classifiers, learned based on different features of a protein) to produce more accurate classifications
  • to build a generic configurable learning tool, that can be used to learn classifiers for other related tasks.
Project Webpage

Learning and Validating Belief Nets

Bayesian belief nets (BN) are becoming the preferred tool for a wide variety of tasks, ranging from sensor fusion to information retrieval. We are currently developing and experimenting with various tools for learning these BNs from training data. We are looking for a student to help us here, both in developing and implementing these learning system, and also in running careful experiments to help us compare these different approaches. We also plan to investigate ways to learn, and use, Probabilistic Relational Models --- extension to belief nets that allow the representation of relationships.

We will also explore ways to compute and use "variance" around the belief net response; see webpage: extending the work on "mixture using variance" and perhaps a variance-based model of value-of-information.

Budgeted Learning

Learning tasks typically begin with a data sample --- eg, symptoms and test results for a set of patients, together with their clinical outcomes. By contrast, many real-world studies begin with no actual data, but instead with a budget --- funds that can be used to collect the relevant information. For example, one study has allocated $30 thousand to develop a system to diagnose cancer, based on a battery of patient tests, each with its own (known) costs and (unknown) discriminative powers. Given our goal of identifying the most accurate classifier, what is the best way to spend the $30 thousand? Should we indiscriminately run every test on every patient, until exhausting the budget? Or, should we selectively, and dynamically, determine which tests to run on which patients? We call this task budgeted learning.

There are many open questions, both theoretic and empirical.

  • Formal analysis: is the task NP-hard given certain standard assumptions?
    Are there any algorithms that are PTAS (approximation algorithms)?
  • Better heuristic algorithms and other efficiency tricks
  • Further empirical studies, over other datasets

Project webpage