Marina Danilevsky

Version 1 by Aaron Williams
on Jan 27, 2012 16:46.

compared with
Current by Marina Danilevsky
on Jan 27, 2012 17:20.

Key
This line was removed.
This word was removed. This word was added.
This line was added.

Changes (7)

View Page History

{float:left}!photo.jpg|thumbnail,align=left!\\

{center}*Marina Danilevsky*{center}
{float}
*Research Advisor:* Jiawei Han
*Contact:* danilev1@illinois.edu

{excerpt}

My current project involves automatically discovering meaningful organizations within information networks (e.g. people who tend to collaborate on papers, terminology which is semantically unrelated but should be lumped together in a domain-specific context, etc). However, constructing meaningful networks from real data, and analyzing them in a reasonable timespan requires thoughtful approaches, often involving parallelization at both the algorithm and coding stages. This is a great opportunity to get some hands-on experience with data mining and information retrieval problems applied to messy real-world data. I am also open to tackling ideas that you propose in this vein - there are so many problems to be solved\!

*Mentee's Commitment:*

Around 3-5 hrs/week
Around 3-5 hrs/week, will vary

*Desired Coursework:*

Preferable that student has parallelization and multi-threaded coding experience. Previous experience with processing large datasets is preferred, as are statistical courses, or statistical / mathematical aptitude. Experience with any data mining / information retrieval /algorithm courses a plus.\\
\\