Explain overfitting, dropout, normalization, RL post-training

Q: Explain overfitting, dropout, normalization, RL post-training

This question evaluates understanding of model generalization and regularization concepts—specifically overfitting, dropout, normalization techniques—and the application of reinforcement learning for post-training alignment in large language models.

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

Machine Learning fundamentals

Answer the following:

What is overfitting? How can it be mitigated in machine learning?
Narrowing to deep learning , what are common approaches to reduce overfitting?
Explain dropout :
- What does it do during training?
- Why is it considered regularization?
- How do you handle it at inference time?
Compare two common normalization methods used in deep nets (e.g., Batch Normalization vs Layer Normalization):
- What statistics do they normalize with?
- How do their behaviors differ for different batch sizes and for sequence models?
- At deployment , which statistics/parameters are used?
Describe common ways reinforcement learning (RL) is used in LLM post-training (alignment/fine-tuning after pretraining).

Explain overfitting, dropout, normalization, RL post-training

Quick Overview

Machine Learning fundamentals

Solution

Comments (0)