Coursera-吴恩达-深度学习-第五门课-序列模型 -week1-测验

本文章内容：

Coursera吴恩达深度学习课程，

第五门课 序列模型(Sequence Models)

第一周 循环序列模型（Recurrent Neural Networks）

测验

Yes, in a language model we try to predict the next step based on the knowledge of all prior steps.

Correct, \Gamma_uΓu  is a vector of dimension equal to the number of hidden units in the LSTM.

 

For the signal to backpropagate without vanishing, we need c^{<t>}c<t> to be dependent on c^{<t-1>}