Students should become familiar with the algorithmic foundations of machine learning, as well as techniques for solving the challenges presented by each dataset. They should be able to select appropriate algorithms for each problem and apply the algorithms to new datasets and understand and evaluate their results.


Learning outcomes and competences
- Understanding of the fundamentals of machine learning algorithms and methodologies presented
- Ability to justify the choice of a machine learning solution to a given problem
- Ability to apply the algorithms to new data sets
- Ability to evaluate the results

- Introduction
- Simple classification and regression models (linear and nearest-neighbour models) and their validation: learning paradigms, loss functions, bias and variance error.

- Model inference methods: Search, Expectation-maximization, clustering.

- Kernel methods.

- Neural networks, deep models and representation learning

- Matrix factorization

- Evaluation of models

- Unsupervised, semi-supervised and weakly supervised pattern discovery.

The predominant teaching methodologies will be the presentation of concepts, using slides and the demonstration of examples in the computer laboratory. Students will be constantly challenged to solve new problems, based on the examples already demonstrated, and to reflect on the results and performance of the storage and processing processes under study.