Notices
Results 1 to 4 of 4

Thread: Dupont Challange

  1. #1 Dupont Challange 
    Forum Freshman Mark Ian's Avatar
    Join Date
    Aug 2009
    Posts
    35
    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!


    Reply With Quote  
     

  2.  
     

  3. #2  
    Forum Isotope
    Join Date
    Feb 2009
    Location
    Transient
    Posts
    2,914
    Fabricating DNA


    Wise men speak because they have something to say; Fools, because they have to say something.
    -Plato

    Reply With Quote  
     

  4. #3  
    Forum Sophomore
    Join Date
    Oct 2010
    Posts
    171
    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.
    Reply With Quote  
     

  5. #4  
    Forum Freshman Mark Ian's Avatar
    Join Date
    Aug 2009
    Posts
    35
    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
    Reply With Quote  
     

Bookmarks
Bookmarks
Posting Permissions
  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •