User:Keki Burjorjee
The account of this former contributor was not re-activated after the server upgrade of March 2022.
Education and Work Experience
Vassar College (1994-1998)
Oracle Corporation (1998-2000)
Brain and Cognitive Sciences Department, University Of Rochester (2000-2002)
Computer Science Department, Brandeis University, (2002-present)
About Me I’m a PhD Student at the DEMO lab of the Computer Science department at Brandeis University. Genetic Algorithms (GAs) are widely used in industry to generate objects of high quality. Yet there is no general consensus about how they "work". I study these algorithms with an eye towards the formulation of a theory of adaptation, i.e. a theory that explains why GAs often generate solutions of increasing quality over time. I believe that the insights gained from this effort will be useful in the construction of more efficient evolutionary algorithms and new machine learning algorithms. I also expect that an accurate theory of adaptation for the genetic algorithm will inform attempts to formulate principled theories of adaptation (with fewer assumptions about the nature of epistasis) in Evolutionary Biology.
Publications • Burjorjee K., Sufficient Conditions for Coarse-Graining Evolutionary Dynamics, Foundations of Genetic Algorithms Conference IX, 2007 (Final Preprint) • Burjorjee K., Pollack J.B., A General Coarse-Graining Framework for Studying Simultaneous Inter-Population Constraints Induced by Evolutionary Operations, Proceedings of the 2006 Genetic and Evolutionary Computation Conference, ACM Press, 2006 (Extended Version with proofs of theorems, Slides) • Burjorjee K., Pollack J.B., Theme Preservation and the Evolution of Representation , Proceedings of the 2nd Indian International Conference on Artificial Intelligence, 2005 • Burjorjee K., Pollack J.B., Theme Preservation and the Evolution of Representation , Proceedings of the Theory of Representation Workshop at GECCO, 2005
Tasks: start a new article • add basic, wanted or requested articles • add definitions • add metadata • edit new pages
Welcome to the Citizendium! We hope you will contribute boldly and well. Here are pointers for a quick start. You'll probably want to know how to get started as an author. Just look at Getting Started for other helpful "startup" links, our help system and CZ:Home for the top menu of community pages. Be sure to stay abreast of events via Twitter. You can test out editing in the sandbox if you'd like. If you need help to get going, the forum is one option. That's also where we discuss policy and proposals. You can ask any administrator for help, too. Just put a note on their "talk" page. Again, welcome and have fun!
-- Sarah Tuttle 09:41, 28 May 2007 (CDT)