The course covers the basics of statistical learning.

• Principal Component Analysis
• Supervised Learning (loss, risk, Bayes classification)
• Multivariate regression (risk analysis)
• Penalized and sparse regression (Ridge, Lasso, risk analysis)
• Kernel-based regression (RKHS)
• Feed forward neural networks (definitions and backpropagation)

• 1 - PCA
  Introduction to numpy, singular value decomposition and principal component analysis from scratch
• 2 - Discriminant Analysis
  Linear and Quadratic discriminant analysis with sklearn
• 3 - Ridge Regression
  Multivariate regression from scratch and with sklearn
• 4 - Lasso Regression
  Lasso regression from scratch and with sklearn
• 5 - Kernel Regression
  Kernel regression from scratch and with sklearn
• 6 - Logistic Regression
  Logistic regression and gradient descent from scratch
• 7 - Gradient descent
  Stochastic gradient descent and coordinate gradient descent from scratch and with torch
• 8 - Feed Forward Neural Networks
  Introduction to dense neural networks with keras and detailed backpropagation from scratch
• 10 - K-means
  Introduction to unsupervised Learning and K-means

• 1 - PCA
• 2 - Bayes classifier
• 3 - Discriminant analysis
• 4 - Regression (i)
• 5 - Regression (ii)
• 6 - Ridge regularization
• 7 - Lasso-based regression
• 8 - Kernel-based regresion
• 9 - Dense neural networks
• 10 - K-means algorithm