Mathematics Diagnostic
Sample the four mathematics topics before choosing focused practice.
Practice
Use a diagnostic to locate gaps, then open only the relevant topic practice.
Search items and build a custom set. Custom sets are saved in this browser.
Diagnostics
Programming Diagnostic
Check Python semantics, data-structure selection, algorithmic control flow, and recursion.
Machine Learning Diagnostic
Sample objectives, updates, model evaluation, representation, networks, and clustering.
Topic practice
Linear Algebra Practice
Cover matrix fundamentals, subspaces, projections, spectral structure, and decomposition.
Calculus Practice
Cover single-variable foundations, multivariable differentiation, approximation, and optimization.
Probability Practice
Move from events and conditioning through moments, distributions, and asymptotic results.
Statistics Practice
Cover estimators, likelihood, Bayesian updating, intervals, tests, and simple regression.
Control Flow Practice
Build reliable branching, iteration, function, comprehension, and trace fluency.
Data Structures Practice
Select and use lists, mappings, sets, stacks, queues, heaps, and graph traversals.
Python Practice
Eliminate mistakes in slicing, sorting, mutability, aliasing, iteration, and complexity.
Recursion Practice
Practice base cases, call traces, and recursive decomposition.
Regression Practice
Connect squared loss, gradients, normal equations, and ridge regularization.
Classification Practice
Connect logistic probabilities and losses to threshold-dependent evaluation.
Convolution Practice
Compute convolution geometry and parameter counts accurately.
Dimensionality Reduction Practice
Relate PCA variance objectives to covariance eigenvectors and SVD.
Gradient Descent Practice
Compute deterministic and stochastic updates and diagnose step-size behavior.
Neural Networks Practice
Practice forward computation, backpropagation, activation behavior, and parameter counting.
Optimization Practice
Relate stationary points, convexity, objectives, regularization, and training diagnostics.
Theory Practice
Reason about bias, variance, overfitting, generalization, and evaluation splits.
Unsupervised Learning Practice
Optimize and interpret hard clustering and mixture-model assignments.