Author: Sune Fischer
Date: 13:00:14 08/04/02
Go up one level in this thread
On August 04, 2002 at 15:43:49, Miguel A. Ballicora wrote: > >5000 parameters is not much when compared to the parameters needed to obtain the >optimal conformation of a protein with a computer. In that case, it is almost >impossible (with the current knowledge) to obtain the right conformation >starting from scratch, but is is very doable when you start from the "optimal" >conformation (determine by physical methods, not by a computer), you change >something and see how the new conformation would look like. Iterations around >the minimum are very fast because all the parameters behave almost linearly or >close enough. When the parameters behave linearly the time to resolve the >problem is O(1) (a linear regresion of n parameters is O(1)). So, even if they >are not perfectly linear, it is way below n log(n). This might not be exactly >like chess but it allows me to make this guess: I believe that learning methods >will be useful to tune all the parameters when a new one has been introduced. >I wonder how many parameters has been throw out in good programs just because >they did not work, but they just needed a general fine tuning of all the rest. > >Regards, >Miguel I agree, but one of the things I've experienced with back propagation, is that the weights oscillate and you don't get closer even when you are not at the minimum. Simple things like a momentum term can increase convergence rate. As the parameters are refined, one needs to adjust the learning rate, that I'm pretty sure of. -S.
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.