News for hackers. Stuff that matters.
Re:Understanding Deep Learning Through Neuron Deletion by LoSboccacc on Friday March 23, 2018 @10:10AM (#16658314)
> but the network could completely fail once 51% of the units are deleted

also the network could have weird results for dropout values around 20%-30% depending on how the robustness was 'learned'

There are no comments on this comment yet.