Re:Neuroevolution of augmenting topologies (NEAT algorithm)
by nurettin on Wednesday December 04, 2024 @02:16PM
(#42320939)
I never understood the appeal of NEAT. It's easy to conceive of mutation operators on fully connected layers instead of graphs of neurons and evaluate a lot faster. NEAT also seems to have at least a dozen hyperparameters.
[ Parent
| on HN ]
Re:Neuroevolution of augmenting topologies (NEAT algorithm)
by Rhapso on Wednesday December 04, 2024 @03:58PM
(#42321989)
It mostly manages its hyperparameters itself.
There is a reward function, one of the hyperparameters we do have to set, for condensing functionality into topology instead of smearing it obscurely across laters. You can just look at a NEAT network analytically and know what is going on there.