Overview of classification algorithms

8 Novembro 2016, 13:00 • João Marques Silva

This week's lecture focused on demonstrating different classification approaches, including decision trees, single and multilayer perceptrons and support vector machines, using R. The experimental setup was also analyzed, and its implementation in R was discussed. The lecture also covered support vector machines, their geometric interpretation, and outlined solution methods, that include quadratic constrained optimization and the use of Lagrangian multipliers. Finally, the lecture also analyzed the derivation of some results related with support vector machines.