ml-recall

#surprisal

1 question from Information Theory

Timed test

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

Take a test

Q 1 / 1Score 0 / 0

Shuffle questions

Question 1: Single choice

mediumAI-checkedInformation Theory

An observer believes the probabilities $Q$ , but the data are actually generated by $P$ . Which quantity is the observer's expected surprisal per observation?

$H(P, Q) = -\sum_j P(j) \log Q(j)$ 1
$H(P) = -\sum_j P(j) \log P(j)$ 2
$H(Q) = -\sum_j Q(j) \log Q(j)$ 3
$D_{\mathrm{KL}}(Q \| P) = \sum_j Q(j) \log \frac{Q(j)}{P(j)}$ 4

Keys: 1–9 select · Enter check / next