I think some of his statements are a little off-base, for instance, regarding the choice of tanh() for the activation function he says: "But mostly it’s 'because it works like this and it doesn’t work when we change…
I think some of his statements are a little off-base, for instance, regarding the choice of tanh() for the activation function he says: "But mostly it’s 'because it works like this and it doesn’t work when we change…