Katkat
Back

Explain learning paradigms, loss, and embeddings

AncestrySoftware Engineer · Technical Screen
MediumSoftware EngineerTechnical ScreenMachine Learning

Last updated

This question evaluates understanding of core machine learning concepts—learning paradigms (supervised, unsupervised, self-supervised), loss functions, and embeddings—and the competency to explain their roles and interrelations in model training and inference.

ML fundamentals (oral)

Answer the following conceptual questions clearly and with examples:

  1. What is supervised learning? What are typical inputs/labels and tasks?
  2. What is unsupervised learning? What problems does it solve?
  3. What is self-supervised learning? How is it different from supervised/unsupervised?
  4. What is a loss function? Why do we need it, and what are a few common examples?
  5. What is an embedding?
  • What does it represent?
  • How is it learned?
  • How is it used at inference time?
  1. Give several real-world use cases for embeddings, especially in personalization or search.