andrewekhalel /MLQuestions
Machine Learning and Computer Vision Engineer - Technical Interview Questions
★ 4,969⑂ 800👁 34⑃ 18● 4▤ 0
4,969
stars
800
forks
34
watchers
18
prs
4
issues
0
releases
README
Machine Learning Interview Questions and Answers (2026) 69 machine learning interview questions with answers, covering ML fundamentals, deep learning, computer vision, NLP, dimensionality reduction, statistics and coding. Curated and community-maintained since 2018. 📖 Also available as a website, browsable by topic: andrewekhalel.github.io/MLQuestions These ML interview questions are useful if you are preparing for a role as: - Machine Learning Engineer - Data Scientist - Deep Learning Engineer - Computer Vision Engineer - NLP Engineer - AI / Research Engineer Contents - Preparation Resources - Machine Learning Fundamentals — 7 questions - Algorithms and Ensembles — 3 questions - Data Preprocessing and Feature Engineering — 4 questions - Optimization and Training — 6 questions - Deep Learning and Neural Networks — 13 questions - Computer Vision — 13 questions - Dimensionality Reduction — 7 questions - Model Evaluation and Validation — 7 questions - Probability and Statistics — 3 questions - Coding and Implementation — 6 questions - NLP Interview Questions and Answers — 13 questions - Contributions Preparation Resources 1. ML Engineer Interview Course 1. Mock ML Interview: Get ready for your next interview by practicing with ML engineers from top tech companies and startups. 1. AI Engineering Interview Prep 1. Generative AI Interviews 1. All of Statistics: A Concise Course in Statistical Inference by Larry Wasserman 2. Machine Learning by Tom Mitchell 3. Designing Machine Learning Systems: An Iterative Process for Production-Ready Applications by Chip Huyen Machine Learning Fundamentals What's the trade-off between bias and variance? If our model is too simple and has very few parameters then it may have high bias and low variance. On the other hand if our model has large number of parameters then it’s going to have high variance and low bias. So we need to find the right/good balance without overfitting and underfitting the data. [[src]](https://towardsdatascience.com/understanding-the-bias-variance-tradeoff-165e6942b229) [[src]](http://houseofbots.com/news-detail/2849-4-data-science-and-machine-learning-interview-questions) Explain over- and under-fitting and how to combat them? [[Answer]](https://towardsdatascience.com/overfitting-vs-underfitting-a-complete-example-d05dd7e19765) ML models learn a relationship between inputs (called training features) and outputs (called labels). After fitting on a training dataset, the model's performance on a held-out test set must be evaluated to determine how well it generalizes to unseen data. Modern ML models have trainable parameters that are learned to build this input-output relationship. The more parameters a model has, the more complex a relationship it can learn between inputs and targets. Underfitting occurs when the flexibility of a model is not sufficient to capture the underlying pattern in a training dataset. Overfitting, on the other hand, occurs when a model is too flexibl