@fchollet During backward step, is it true to say that gradient of L1 will not contain any partial derivative of L2 parameters?
@pommedeterre33 Right. The gradient is inferred automatically at each node following standard backprop rules.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet in multi task learning in graph#nnet on Keras: there is 1 gradient descent per task and per batch, right? http://www.thespermwhale.com/jaseweston/papers/unified_nlp.pdf …Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.