CMU Deep Learning 2018 by Bhiksha Raj 学习记录(12) Lecture 13: Recurrent Neural Networks 3

 

 

 

 

 

 

 

Div(Y(1),...,Y(t),Y_target(1),...,Y_target(t)) ≠ ∑Div(Y(i),Y_target(i))

 

 

 

 

Recurrence is not necessary.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

  http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

P means Period(Section), I think.