Re:Neuroevolution of augmenting topologies (NEAT algorithm)
by PartiallyTyped on Wednesday December 04, 2024 @11:43AM
(#42319247)
We can also show that sparse NNs under some conditions are ensembles of discrete subnets, and the authors of the original dropout paper argue that [dropout] effectively creates something akin to a forest of subnets all in "superposition".
[ Parent
| on HN ]
There are no comments on this comment yet.