From: Dan Fabulich (daniel.fabulich@yale.edu)
Date: Tue May 23 2000 - 03:09:01 MDT
Martin Ling, missing the point, replied:
> On Tue, May 23, 2000 at 12:19:15AM -0400, Dan Fabulich wrote:
> > Matt Gingel noted briefly:
> >
> > > In the general case, evolution is a graph search. Each possible
> > > individual is a node, and mutations spell out the transition rules. By
> > > manipulating the space of transition rules, we transform the search
> > > space - we make some points closer together and some further
> > > apart. Perhaps more importantly, local maxima can be eradicated
> > > since we change the set reachable nodes. (This analysis still
> > > holds if we consider crossover operators, every node becoming a
> > > population.)
> >
> > Here's a good example of how someone might use GAs: they might be
> > interested in finding out what the most aerodynamic design for a
> > vehicle is. So they'd design a multi-dimensional space allowing for a
> > variety of different things to be changed in the design of the craft.
> > Then, they'd set the GA to work.
> >
> > When it got to work, it would generate a random sampling of designs,
> > CHECK TO SEE HOW AERODYNAMIC THEY WERE, and prioritize the designs
> > which were the most aerodynamic in the next run, which would amount to
> > random variations, breedings, etc. from the previous generation.
> >
> > So. GA. Trying to generate good heuristics. It generates a random
> > sampling of heuristics (or sets of heuristics). Then it checks to see
> > which heuristics are best, and prioritizes the best heuristics in the
> > next generation.
> >
> > But how do you figure out whether a heuristic is good or not? Well,
> > heuristics are rules for action. You USE the heuristic, and you see
> > how well off you wind up. (Using some definition of "well off" which
> > has nothing to do with motivations, I suppose.) In fact, just one
> > trial run really isn't enough... you need to try using the heuristic
> > many many times in order to even out statistical hiccups.
>
> ...so you have a second genetic algorithm, trying out different
> heuristics on the first. And then, if neccessary, one above that.
>
> Has this been tried? Meta-design? Meta-meta-design?
OK, *now* I'm frustrated. [I left my whole post here so you can
reread it.]
You COMPLETELY missed the point here. How do you know if ANY of your
heuristics are good? A single god damned one of them? Answer: you
don't, without testing. Since you can't tell if any of your
*heuristics* are good, you also can't tell if any *heuristic search
engines* (meta-designs) are good, because they're only as good as the
heuristics they find/generate, and *you don't know how good that is*.
You can't just run another heuristic search, because you have no way
of knowing whether any of your heuristics are good AT ALL without
testing them.
If you have no way of finding values (such as the drag coefficient),
you have no way of finding maximum values. Common sense, people.
GAs, hell, ANY form of calculation, including "brute force the entire
search space," won't work unless you actually have some values to
search on.
You can't even search for the best COFFEE MAKER like this, guys! How
do you know if any of your recipes are good? No amount of pure
calculation will find the best coffee recipe, nor will it find you the
best way to calculate the best coffee recipe, NOR will it find you the
best way to calculate the best way to calculate the best coffee
recipe. It can't BE calculated. You have to *test*.
You're searching on a table of UNKNOWN VALUES. Does this mean
anything to you? We're talking fundamentally UNDERIVABLE here.
I swear, it's like they think you really CAN derive the existence of
tapioca pudding...
-Dan, who needs to get out more
-unless you love someone-
-nothing else makes any sense-
e.e. cummings
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 15:28:46 MST