Skip to content
ml-recall

#perplexity

4 questions from Dimensionality Reduction, Language Modeling

Timed test

4 questions · 4 min · score and explanations at the end

Take a test
Q 1 / 4Score 0 / 0

Question 1: Short answer

easyAI-checkedDimensionality Reduction

In t-SNE, the hyperparameter is, loosely, a guess at the number of close neighbours each point has. Lower values make the embedding pay more attention to structure and less to global structure.

Fill in every blank (hints in the boxes). Enter moves to the next blank.