Skip to content
ml-recall

#l2-normalization

1 question from Transfer Learning

Timed test

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

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

mediumAI-checkedTransfer Learning

An image-retrieval system L2-normalizes every 512-dimensional ResNet-34 embedding (divides it by its Euclidean norm) before storing it. Two stored embeddings have cosine similarity 0.8. What is the Euclidean distance between them? Round to 3 decimals.

a number, 3 decimals