Explain Core ML Fundamentals
Company: UiPath
Role: Machine Learning Engineer
Category: Machine Learning
Difficulty: easy
Interview Round: Technical Screen
During a machine learning screening, the candidate was asked a set of rapid-fire fundamentals questions. Answer the following in a concise but correct way:
1. What loss functions are commonly used for regression, and what is the derivative of mean squared error with respect to the prediction?
2. If a model is overfitting, what techniques can be used to reduce overfitting?
3. What are common activation functions, and when are they typically used?
4. What is dropout, and how does it help?
5. State the formulas for the dot product of two vectors, cosine similarity, Euclidean distance, Manhattan distance, and a common normalization method.
6. You are building a house-price prediction model with two raw features: floor area and neighborhood. What feature engineering or preprocessing steps would you consider before training?
Quick Answer: This question evaluates mastery of core machine learning fundamentals—loss functions and derivatives, regularization and overfitting mitigation, activation functions and dropout, similarity and distance metrics, and feature engineering for predictive models.