Return values from calling LSTM_cell in Jazz assignment

Course Q&A Deep Learning Specialization Sequence Models
1

Hello, I’m curious about this line:

next_hidden_state, _, next_cell_state = LSTM_cell(inputs=input_x, initial_state=[previous_hidden_state, previous_cell_state])

From the videos, next_hidden_state is a, next_cell_state is c.
Is the throwaway variable the output prior to the softmax activation? I.e. Wya @ a ?

2

To find this, you have to look at the classes that the Keras LSTM layer inherits from.

1 Like