Explain BatchNorm, optimizers, and L1/L2

Q: Explain BatchNorm, optimizers, and L1/L2

This is a Machine Learning interview question from Snapchat for Machine Learning Engineer roles. View the full question and solution on PracHub.

Q: How do I approach Machine Learning interview questions?

Machine Learning questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master machine learning interviews.

Question

Loading...

Prompt

Answer the following ML fundamentals questions:

Batch Normalization (BatchNorm):
- What trainable parameters does BatchNorm have?
- What statistics are used during training vs inference?
- Why does BatchNorm help optimization, and what are common pitfalls?
Optimizers: Compare SGD, Momentum, RMSProp, and Adam.
- What problem does each address?
- When might plain SGD generalize better than Adam?
Regularization: Compare L1 and L2 regularization.
- How do they affect weights and sparsity?
- How do they relate to MAP estimation (priors) if you know that framing?

Explain BatchNorm, optimizers, and L1/L2

Prompt

Solution

Comments (0)