Music interference model

[mc04xkf]

In music interference model of assignment 3, it selects the most probable during sampling.
This will always generate the same result given an initial input, won’t it ?

In contrast, in assignment 2, we sampled the dinosaur name randomly.

Is my understanding correct ? If yes, Why is the difference ?

[TMosh]

Please see this thread:

W1 A3 Jazz Music music_inference_model

In this assignment, in 2.D, we have to convert the output from the previous LSTM cell into a new input for the current LSTM cell, and we are instructed to do this in 2 steps: Get the index of the maximum value of the predicted output using tf.math.argmax along the last axis. Convert the index into its n_values-one-hot encoding using tf.one_hot. I am confused here, as to why we are instructed to find the index of the maximum value. If we will do this, then won’t we always sample the same music…