An initial round (background/ profile based), a simple classification problem as homework, a technical interview (mostly based on how the solution was framed for the homework), an interview with a non-technical person, and a final round with their co-founder. 1. Why does multicollinearity happen in regression? 2. Working of boosted trees 3. Types of regularization 4. Overfitting and underfitting
- what is a support vector machine? - what's the difference between a Support Vector Machine (SVM) and a linear classifier? - why do I encode visual data and do not feed the SVM with raw information? - what are the convolutional neural networks and how do they work? - how would I treat a picture of a person that wear zalando clothes? - how could I deal with a multiclass classification problem with 1,000,000 different classes? - how could I possibly help zalando to improve their services?
Burning Wire Problem was asked 3 bulb puzzle was asked
If we train a network using only one image of cat. What is the output if we flip that image?
What is boosting
If you were designing a robot lawnmower, where would you start?
Tell us about a time that you did xyz at work... even if nothing remotely like this ever happened.
Grammar, why should we hire you, what is machine learning, previous experience etc.
About project in my final year
Why is your published paper devoid of a proper formulation?
Viewing 791 - 800 interview questions