Fundamentos

Sesión 1: Guillermo Moncecchi (Repaso de álgebra lineal)
Sesión 2: Jairo Bonanata (Regresión lineal, regresión logística, gradient descent)
Sesión 3: Raúl Garreta (Redes Neuronales y Backpropagation)

• Repaso de álgebra lineal (Matrices con Python y Numpy)
  

• Repaso de regresión lineal, regresión logística. Gradient descent.

• Redes neuronales y backpropagation (Artificial Neural Networks and Backpropagation)
  

Material

• Matrices con Python y Numpy
  

• Linear Algebra Review and Reference

• A Beginner’s Guide to Eigenvectors, PCA, Covariance and Entropy

• A tutorial on PCA (Lindsay Smiths)
• PCA Step by step in Python (Sebastian Raschka)
• Machine Learning - Ng (Stanford) - II, III, IV, VI, VII
• Logistic Regression  - del libro Advanced Data Analysis from an Elementary Point of View (Cosma Rohilla - Carnegie Mellon)
• Gradient Descent Example
  
• An overview of gradient descent optimization algorithms - Sebastian Ruder
• Fitting a model via closed-form equations vs. Gradient Descent etc. - Sebastian Raschka
• (Physio)logical circuits: the intellectural origins of the McCulloch - Pitts Neural Networks - Tara Abraham
• Calculus on computational graphs: backpropagation - Crhis Olah
• Neural Networks and Deep Learning - Chapter 2 - Michael Nielsen
• Neural Networks and Deep Learning - Chapter 1 - Michael Nielsen
• Notas del curso de Socher (parte III)