Explain learning paradigms, loss, and embeddings
Company: Ancestry
Role: Software Engineer
Category: Machine Learning
Difficulty: medium
Interview Round: Technical Screen
## 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?
6. **Give several real-world use cases for embeddings**, especially in personalization or search.
Quick Answer: 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.