Lectures

  • Lecture October 4, 2016 - Introduction to Matlab (optimization toolbox) 
  • Lecture October 5, 2016 - The perceptron algorithm (Ref. Slide 4th lecture, Teching notes chapt.2, P. Domingos - A few useful things to know about Machine Learning). Brief review on optimization problems and optimization algorithm: basic defintions, convex problems, optimality conditions, unconstrained algorithms.
  • Lecture October 11, 2016 - Multiplayer perceptron: (Ref. Slide 5th Lecture, teaching notes chapt. 3)
  • Lecture October 12, 2016 - Multiplayer perceptron: back propagation algorithm, Batch BP : convergence theorem (Ref. Slide 6th Lecture, teaching notes chapt. 3)
  • Lecture October 18, 2016 - Online methods: incremental/stochastic gradient. Global optimization for MLP  (Ref. Teaching notes chapt. 3)
  • Lecture October 19, 2016 - RBF, Regularized RBF Network  (Ref. Slide 8th Lecture)
  • Lecture October 25, 2016 - Generalized RBF Network: unsupervised selection of centers
  • Lecture October 26, 2016 - Generalized RBF Network: supervised selection of weights and centers. Two block decompostion methods, exact and inexact solution of subproblems, convergence properties. Decomposition methods: block learning of centers
  • MIDTERM November 2, 2016 -
  • Lecture November 8, 2016 - Hard SVM: generalities, defintion of margin, defintion of the max margin problem (Ref. Slide 11th lecture)
  • Lecture November 9, 2016 - Preliminaries on constrained optimization. Soft C-SVM (Ref. Slide 12th lecture)
  • Lecture November 15, 2016 - Duality in convex Quadratic Programming
  • Lecture November 16, 2016 - The dual problem of hard-SVM and C-SVM.