What does the architecture of Word2Vec training look like? How does the model predict the missing word based on context?
Machine Learning / AI
Do you have experience with RecSys or LLM?
What acts as weights in gradient boosting?
How does Random Forest affect bias and variance?
Tell me about Momentum: what are its features?
How to change parameters? How to understand in which direction to change?
How are features selected in a Random Forest?
What data structure in Python allows modeling NoSQL databases?
How do you obtain a large text embedding (e.g., a long product description) for classification tasks?
Tell me about gradient descent: how it works and what are its modifications (SGD, Momentum, Adam)?
Tell me about decision trees: how is a tree built and how does inference occur?
What other NLP experiences and tasks have you worked on?
Do you only write in Python or in other languages as well?
How to reverse an array without using compilation?
Do you have a military ID or registration card?