Question 1: Single choice
mediumAI-checkedInformation TheoryWord distributions estimated from small counts often contain zero probabilities. Which of these measures between two distributions and can become infinite because of such a zero?
3 questions from Information Theory, Generative Adversarial Networks
3 questions · 3 min · score and explanations at the end
Word distributions estimated from small counts often contain zero probabilities. Which of these measures between two distributions and can become infinite because of such a zero?