Thread: Dupont Challange

You may or may have not heard of this challange, basically its an essay that I'll write and win a cash prize and a visit to nasa to witness a shuttle launch... This would be my second try, I submitted a paper last year on soliton waves in the brain, but I did not win . Thats why I need YOUR help picking and reviewing my essay in the course of the next few months. The first stage is choosing the topic, preferrably having to do with biology and has to be cutting edge and recent discovery. So suggest away!

Fabricating DNA

I won't give you a subject but a method and a tool which can be used to solve problem. When you will see the tools, you might say "Yes, it is exactly what we will need to do that !". And you will have an idea of subject.

I recently wrote a paper on application of symbolic regression in petrophysics (a branch of geology). It had a pretty fair success internally and it's going to be presented now externally.
Symbolic regression using genetic programming is a hot subject at the moment, application in biology are legions. I just suggest you investigate that direction, just type "eureqa" in Google and you will find it. Look at the papers already written in the biology domain.

I think symbolic regression could be very interesting to model complex subjects in biology that have not yet been explored through this method (although, caution, I am not biologist !). I think about population biology, how you could model the evolution of some populations under some constraints. In fact, symbolic regression is great as it allows to get rid of the black box of most artificial intelligence model like neural network, self organizing maps etc... You combine both the stochastic approach and then you come back to a deterministic law with a certain uncertainty. It's lovely and very elegant.

I've started researching symbolic regression on the web, its seems like an interesting topic that I'll look into more... I'm not sure if it is 'cutting edge' enough tho