Monday, August 17, 2015

My My such a long time  between posts
Life goes on.
Still wrestling with complex systems.
Economics is interesting in this area as is Climate Models.
Making progress.
All the more reason for heuristic explorations. Poke it with a stick and write down the results.
Sir Francis Bacon was not wrong.

Found an ex IBM anthropologist taking the same approach as I decided years ago.
Curiously I met him once.

I am surprised to find have the same difficulties semi physical sciences with the verification and validity of models.

I found this example of chasing down Von Neuman's elephant. Wonderful story, as told by Fermi to Dyson and recited by Feynman. Trying to add Shrodingers cat to my cat stories. elusive. On a Lewis Carroll note what if Schrodinger's cat, Von Neuman's elephant and Nassim Taleb's Black swans had a round table discussion. Might give us caution about what certainty we attach to what we think we know.

 And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See
And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See more at: http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html#sthash.J6lQ6pFg.dpuf
And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See more at: http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html#sthash.J6lQ6pFg.dpuf
And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See more at: http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html#sthash.J6lQ6pFg.dpuf

And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See more at: http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html#sthash.J6lQ6pFg.dpuf
And making elephants dance is indeed what modeling in drug discovery runs the risk of doing, especially when you keep on adding parameters to improve the fit (Ah, the pleasures of the Internet - turns out you can literally fit an elephant to a curve). This applies to all models, whether they deal with docking, molecular dynamics or cheminformatics. This problem of overfitting is well-recognized, but researchers don't always run the right tests to get rid of it. As Derek pointed out however, the problem is certainly not unique to drug discovery. He started out by describing the presence of "rare" events in finance related to currency fluctuations - these rare events happen often enough and their magnitude is devastating enough to cause major damage. Yet the models never captured them, and this failure was responsible at least in part for the financial collapse of 2008 (this is well-documented in Nassim Taleb's "The Black Swan"). - See more at: http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html#sthash.J6lQ6pFg.dpuf

http://wavefunction.fieldofscience.com/2015/02/derek-lowe-to-world-beware-of-von.html

No comments:

Post a Comment