Skip to content
ml-recall

#soft-targets

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

Question 1: Single choice

mediumAI-checkedInformation Theory

A training example has the soft target q=(0.8,0.2,0)q = (0.8, 0.2, 0) over three classes. What is the smallest cross-entropy H(q,p)H(q, p) (natural log) that any predicted distribution pp can reach, and at which pp?

Choose one option