ml-recall

#vanilla-rnn

1 question from Recurrent Neural Networks

Timed test

1 question · 1 min · score and explanations at the end

Take a test

Q 1 / 1Score 0 / 0

Shuffle questions

Question 1: Short answer

mediumAI-checkedRecurrent Neural Networks

A vanilla RNN computes $\mathbf{h}_t = \tanh(\mathbf{W}_{xh}\mathbf{x}_t + \mathbf{W}_{hh}\mathbf{h}_{t-1} + \mathbf{b}_h)$ and $\mathbf{o}_t = \mathbf{W}_{hq}\mathbf{h}_t + \mathbf{b}_q$ . The input size is 3, the hidden size 4 and the output size 2, and the network is unrolled over 5 time steps. How many trainable parameters does it have, biases included?

Enter: check / next