neural network - Clockwork RNN (CW-RNN) and TanH activation function -


thanks again taking time answer post !

quick question :
in clockwork reccurent neural network (rnn), (here documentation),
seems me tanh-activated output layer suffer extreme load many connections, , alway output near 1 , or mistaken ?

let's have cw-rnn with, hidden layer, 4 modules of 50 neurons each.

even if these modules have different clock rate, sometimes, more 1 module activate & output else 0 : thus, output layer may output 1 because of many inputs.

is there missing in cw-rnn concept ?
know weight initialization, i'm wondering if missing piece of puzzle.


Comments

Popular posts from this blog

javascript - Confirm a form & display message if form is valid with JQuery -

Retrieving ETA (estimated time of arrival) with Google Distance Matrix API and public transit as transport mode -

ionic framework - Meteor - Error: Failed to execute 'insertBefore' on 'Node' -