Re:Self-Assembling Artificial Neural Networks Through Neural...
by mnky9800n on Wednesday October 04, 2023 @09:49AM
(#37765142)
> There are a few problems with this approach though. For one, there are often many local maxima that a genetic algorithm can easily converge on.
> Secondly, the state space is often enormous, and testing/discarding millions of generations of poorly constructed networks is a very inefficient way of sampling it.
> Secondly, the state space is often enormous, and testing/discarding millions of generations of poorly constructed networks is a very inefficient way of sampling it.
This is true for the living as well.