LHLearning Hub
← Biblioteca

Ruta de aprendizaje

Math for Machine Learning

Un currículo para dominar las matemáticas detrás del machine learning.

0%
0 de 34
dominadas
02

10 unidades

Linear Algebra

El lenguaje de los datos: vectores, matrices y transformaciones.

  1. LA-01 — Vectors→
  2. LA-02 — Vector spaces, span, basis→
  3. LA-03 — Matrices & linear maps→
  4. LA-04 — Systems, Gaussian elimination, rank→
  5. LA-05 — Inverse & determinant→
  6. LA-06 — Orthogonality, projections, Gram–Schmidt→
  7. LA-07 — Eigenvalues, eigenvectors, diagonalization→
  8. LA-08 — Symmetric matrices, quadratic forms, positive definiteness→
  9. LA-09 — SVD & matrix decompositions→
  10. LA-10 — Applications: PCA & least squares→
03

10 unidades

Calculus

Cómo cambian y aprenden los modelos mediante gradients y optimization.

  1. Calc-01 — Functions, limits, continuity→
  2. Calc-02 — Derivatives (single variable)→
  3. Calc-03 — Optimization (single variable)→
  4. Calc-04 — Integration essentials→
  5. Calc-05 — Partial derivatives & gradient→
  6. Calc-06 — Jacobian & Hessian→
  7. Calc-07 — Multivariable chain rule & backpropagation→
  8. Calc-08 — Taylor series & approximation→
  9. Calc-09 — Matrix calculus→
  10. Calc-10 — Optimization: gradient descent, convexity, Lagrange→
04

9 unidades

Probability & Statistics

Razonamiento bajo incertidumbre, distributions y estimación.

  1. Prob-01 — Foundations & combinatorics→
  2. Prob-02 — Conditional probability & Bayes→
  3. Prob-03 — Random variables & distributions→
  4. Prob-04 — Expectation, variance, moments→
  5. Prob-05 — Common distributions→
  6. Prob-06 — Joint distributions, covariance, independence→
  7. Prob-07 — Estimation: MLE & MAP→
  8. Prob-08 — Sampling, CLT & inference→
  9. Prob-09 — Information theory: entropy, cross-entropy, KL→

Antes de empezar

Prepara tu sistema.

Cómo estudiar→Recursos→Setup→