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>}