← Back to categories

Foundations

Probability & Statistics

8 questions

Multiple Choice

Central Limit Theorem Application

Variance of Sum of Random Variables

Interpreting P-Values

Conditional Probability in Medical Testing

Open-Ended

Bayes' Theorem and Posterior Updating

Common Probability Distributions in ML

Statistical Significance and Hypothesis Testing in ML

Maximum Likelihood Estimation and Loss Functions

Linear Algebra Essentials

8 questions

Multiple Choice

Matrix Multiplication Dimensions

Eigenvalue Interpretation in PCA

Rank and Linear Dependence

SVD for Recommender Systems

Open-Ended

Matrix Operations in Machine Learning

Eigenvalues and Eigenvectors in ML

SVD and Dimensionality Reduction

Vector Spaces, Basis, and Projections

Optimization Fundamentals

8 questions

Multiple Choice

Gradient Descent Step Direction

Learning Rate Selection Impact

Convexity and Global Optima

Momentum in Optimization

Open-Ended

Learning Rate Selection and Scheduling

Gradient Descent Variants and Convergence

Convex vs Non-Convex Optimization

Local Minima, Saddle Points, and Escaping Them

Information Theory

7 questions

Multiple Choice

Entropy and Uncertainty

Cross-Entropy Loss Interpretation

KL Divergence Properties

Mutual Information for Feature Selection

Open-Ended

Entropy in Machine Learning

KL Divergence and Cross-Entropy Loss

Mutual Information and Feature Selection

Learning Theory

8 questions

Multiple Choice

Bias-Variance Tradeoff

VC Dimension Application

Generalization Gap

No Free Lunch and Model Selection

Open-Ended

Why Models Generalize Beyond Training Data

No Free Lunch Theorem

PAC Learning Framework

VC Dimension and Model Capacity

Computational Complexity

7 questions

Multiple Choice

Big-O Notation Comparison

Space-Time Tradeoffs in ML

Transformer Attention Complexity

NP-Hardness in ML

Open-Ended

Time Complexity of ML Algorithms

Memory Requirements and Batch Processing

When Algorithms Break at Scale