Print

Print


While Michael and Hod may well have something good here, it's  
important to note that computational effort is (at least for me) a  
very heavily frowned-upon measure for a good many reasons.   
Computational effort results are suspect.

Sean

On Oct 12, 2010, at 7:52 AM, William Tozier wrote:

> http://portal.acm.org/citation.cfm?id=1830483.1830584
>
> Basically what Michael did was school all of us who have been using  
> the convoluted original ALPS architecture (Greg included) on how  
> much simpler and more effective it can be to simply:
>
> * keep track of the "age" (I prefer "progress") of every solution in  
> the population
> ** randomly generated solutions have progress=0
> ** solutions generated by applying search operators are one more  
> than the max progress of any contributing parent
> * select for minimum error AND minimum progress using your favorite  
> multiobjective approach