Lensa ML
Track 1 of 6

Foundations

Calculus, linear algebra, and probability: the tools every model is built from.

Start here if you want the math first, or come back to it from any later track. 3 paths · 20 explainers.

Path 01 · 7 explainers

Calculus for ML

Derivatives, the chain rule, and the optimization math behind training

  1. 1Derivatives
  2. 2The Chain Rule
  3. 3Partial Derivatives & Gradients
  4. 4Logarithms & Exponentials
  5. 5Matrix Calculus & Jacobians
  6. 6Convexity, Minima & Saddle Points
  7. 7Constrained Optimization
Path 02 · 5 explainers

Linear Algebra

Vectors, tensors, eigenvalues, and the decompositions ML relies on

  1. 1Linear Algebra
  2. 2Tensors, Broadcasting & Reshaping
  3. 3Norms & Distance Metrics
  4. 4Eigenvalues & Eigenvectors
  5. 5Singular Value Decomposition
Path 03 · 8 explainers

Probability & Statistics

Distributions, Bayes, estimation, and information theory end to end

  1. 1Probability & Distributions
  2. 2Statistics Essentials
  3. 3Bayes' Theorem
  4. 4Hypothesis Testing
  5. 5Sampling & Monte Carlo
  6. 6MLE & MAP Estimation
  7. 7Entropy & Cross-Entropy
  8. 8KL Divergence