Sumários

Classification - II

27 Novembro 2024, 08:30 • André Maria da Silva Dias Moitinho de Almeida

  • Overview of supervised classification
    • Relation with regression
    • Validation
    • Decision boundaries
  • Supervised methods:
    • K-Nearest Neighbours

Classification - I

26 Novembro 2024, 14:00 • André Maria da Silva Dias Moitinho de Almeida

  • Goal: to assign data to discrete classes or categories. 
  • Overview of classification types: unsupervised and supervised
  • Performance metrics: Completeness, Contamination, Precision, Recall 
  • Unsupervised classification
    • With clustering methods 
    • With dimensionality reduction methods

Optimisation

20 Novembro 2024, 09:30 • André Maria da Silva Dias Moitinho de Almeida

Computational exercises on optimisation

Optimisation - III

20 Novembro 2024, 08:30 • André Maria da Silva Dias Moitinho de Almeida

  • Approaches (cont)
    • Markov Chain Monte-Carlo algorithms
      • Metropolis-Hastings
      • Gibbs
      • Parallel tempering
    • Integrated nested Laplace approximations (INLA)

Optimisation - II

19 Novembro 2024, 14:00 • André Maria da Silva Dias Moitinho de Almeida

  • Approaches (cont)
    • Gradient descent generalizations (brief mention): Stochastic Gradient Descent (SGD) with mini-batches; Adding momentum (GDM); AdaGrad (Adaptive Gradient Algorithm); RMSprop; ADAM (Adaptive Gradient Algorithm)
    • Markov Chain Monte-Carlo - theoretic foundations