Compare knowledge distillation vs transformers
Last updated: February 11, 2026
Quick Overview
Discuss the trade-offs between batch normalization and contrastive learning for document classification.
Expedia
February 11, 20264
7
123 solved
Discuss the trade-offs between batch normalization and contrastive learning for document classification.
Machine learning questions at Expedia test both theoretical understanding and practical experience. This Onsite question evaluates your knowledge of ML fundamentals and your ability to apply them to real-world problems.
What the Interviewer Expects
- Explain the concept clearly with intuitive examples
- Discuss when and why to use this technique
- Identify common pitfalls and how to avoid them
- Compare with alternative approaches at a high level
Key Topics to Cover
How to Approach This
- Understand the bias-variance trade-off. High training accuracy but low test accuracy signals overfitting.
- Choose evaluation metrics carefully based on the problem. Accuracy alone is often insufficient.
- Feature engineering is often more impactful than model selection.
- Know when to use tree-based models (tabular data) vs neural networks (unstructured data).
- Handle class imbalance with SMOTE, class weights, or appropriate loss functions.
Possible Follow-up Questions
- How would you ensure reproducibility in your ML pipeline?
- What are the computational costs of this approach at scale?
- How would you detect and handle concept drift?
- How would you explain this model's predictions to a non-technical stakeholder?
Sharpen Your Skills on Codemia
Practice similar problems with our interactive workspace, get AI feedback, and track your progress.
Explore ML Interview PrepSample Answer
Core Concept: Batch Normalization
Batch normalization is a technique used to improve the training of deep neural networks by normalizing the inputs to each layer. This helps to mitigate issues like internal covariate shift, where the ...
Core Concept: Contrastive Learning
Contrastive learning is a self-supervised learning method that involves training a model to distinguish between similar (positive) and dissimilar (negative) pairs of data points. The framework encoura...
Submit Your Answer
