Explain Core ML Concepts
Company: Snapchat
Role: Machine Learning Engineer
Category: Machine Learning
Difficulty: medium
Interview Round: Onsite
Answer the following machine learning fundamentals questions:
1. Explain the difference between batch normalization and layer normalization. Discuss how each computes statistics, where each is typically used, and their practical trade-offs.
2. What is model calibration? How would you evaluate whether predicted probabilities are calibrated, and how can calibration be improved?
3. How would you handle an imbalanced dataset during training, evaluation, and threshold selection?
Quick Answer: This question evaluates understanding of core machine learning fundamentals—normalization techniques (batch versus layer), probabilistic model calibration, and strategies for handling imbalanced datasets across training, evaluation, and threshold selection.