Math for ML

Vectors, matrices, probability and optimisation, each implemented by hand so the formulas stop being abstract.

Beginner · 18 problems · 0 passed · Background reading: Linear Algebra for AI

1. 01Dot Product From Scratcheasy
2. 02Matrix Multiplication From Scratchmedium
3. 03Euclidean and Manhattan Vector Normseasy
4. 04Vector Projection and Rejectioneasy
5. 05Matrix Determinant for Low-Order Systemseasy
6. 06Sample Mean and Variance From Scratcheasy
7. 07Sample Covariance Matrixmedium
8. 08Bayes' Rule Categorical Posteriormedium
9. 09Shannon Entropy, Cross-Entropy, and KL Divergencemedium
10. 10Central Finite Difference Gradient Approximationmedium
11. 11Jacobian Matrix Evaluationmedium
12. 12Classical Momentum Gradient Descent Stepmedium
13. 13Newton-Raphson Optimization Stepmedium
14. 14Power Iteration for Dominant Eigenpairmedium
15. 15Matrix Inverse via Gauss-Jordan Eliminationmedium
16. 16Gram-Schmidt Orthonormalizationeasy
17. 17Numerically Stable Softmax and Cross-Entropyhard
18. 18Conjugate Gradient Method Single Iterationhard

Next track: Classical ML from Scratch