Browsing Faculté des arts et des sciences by Subject "Self Attentive Networks"
Now showing items 1-1 of 1
-
Towards better understanding and improving optimization in recurrent neural networks
(2020-12-16)Recurrent neural networks (RNN) are known for their notorious exploding and vanishing gradient problem (EVGP). This problem becomes more evident in tasks where the information needed to correctly solve them exist over long time scales, because it ...