I want to analize a network such that all neurons of its hidden layers output LogisticSigmoid[w.x+b]
, which is one of the most common ouputs analized in a neuron. Is there a way to combine LinearLayer[]
that gives output w.x+b and the LogisticSigmoid
function? I looked for an option of changing the activation function in LinearLayer[]
but I did not find it.
Note: I do not want to use twice ammount of hidden layers by first applying LinearLayer[]
and then ElementWiseLayer[LogisticSigmoid]
, I would like the network to be more compact.
How would I do that?
ElementWiseLayer
doesn't contain any parameters, it's the same as changing activation function forLinearLayer
. You don't even have to applyElementWiseLayer
, justLogisticSigmoid
works. $\endgroup$ – swish Apr 10 '18 at 17:45