- Generic: 1.1. Basic general knowledge 1.2. Ability to analyse and synthesise 1.3. Ability to apply knowledge in practice 1.4. problem solving 1.5. Ability to integrate knowledge - Cognitive: 2.1. Knowledge of the typology of astronomical data. 2.2. Understanding of the nature of data according to instrumentation. 2.3. Statistical processing of time series. 2.4. Image processing 2.5. Bayesian inference, inversion problem, parametric modelling. 2.6. Non-parametric modelling. 2.7. Classification problems. - Procedural/Instrumentation 2.8. Use of software for data modelling. 2.9. Use of machine learning methods for time series modelling and prediction. 2.10. Deep learning for classification, neural networks, supervised and unsupervised learning.

K3: To know fundamental contents in their area of study starting from the basis of general secondary education and reaching a level proper of advanced textbooks, including also some aspects of the forefront of their field of study. S1: To plan and organize team work making the right decisions based on available information and gathering data in digital environments. S3: Ability to solve technological, computer, mathematical and statistical problems that may arise in data engineering and science, applying knowledge of mathematics, probability and statistics, programming, databases, and languages, grammars and automata. S4: Ability to solve mathematically formulated problems applied to various subjects, using numerical algorithms and computational techniques, and applying knowledge of: algebra; geometry; differential and integral calculus; numerical methods; numerical algorithms; statistics and optimization S5: Ability to correctly identify predictive problems corresponding to certain objectives and data, based on knowledge of algorithms, modeling, prediction and filtering, and to use the basic results of regression analysis as the basis for prediction methods S6: Ability to correctly identify classification problems corresponding to certain objectives and data, based on knowledge of algorithms, modeling, prediction and filtering, and to use the basic results of multivariate analysis as the basis for classification, clustering and dimension reduction methods S7: Capability for mathematical modeling, algorithmic implementation and optimization problem solving related to data science, relying on knowledge of mathematics, algorithms, programming and optimization. S9: Apply, design, develop, critically analyze and evaluate machine learning methods in classification, regression and clustering problems and for supervised, unsupervised and reinforcement learning tasks. S10: Apply, design, develop, critically analyze and evaluate solutions based on artificial neural networks S11: Apply, design, develop, critically analyze and evaluate solutions based on machine learning for applications in specific domains such as recommendation systems, natural language processing, Web or social networks S16: Ability to synthesize the conclusions obtained from the analyses carried out and present them clearly and convincingly both in writing and orally to both specialized and non-specialized audiences

Unit 1. Model parameter estimation. Parametric models. Time series in Astrophysics. Light curves, radial velocity curves and gravitational waves. Bayesian inference: MCMC and Importance sampling. Unit 2. Model selection. Cosmological model. Flare oscillations. Number of exoplanets. Hypothesis testing, Bayesian evidence, Nested Sampling. Unit 3. Gaussian processes for non-parametric fitting. Emission and absorption lines. Light curves of eclipsing binaries. Transiting exoplanets. Unit 4. Machine learning tools. Astronomical images, time series and spectral classification. 1D and 2D neural networks. Clustering. K-means. Gaussian mixture models. Unit 5. Other deep learning tools. Pattern detection/recognition in time series. Unsupervised learning.

The course will be taught in two types of classes: theory and computational practice. THEORY (2 ECTS) The sessions explain the basic fundamentals and analysis tools corresponding to the core of the course. Numerous examples of real data, their properties and behaviour will be provided. For this purpose, a blackboard and audiovisual media (slides, video, ...) will be used. Machine and deep learning methods appropriate to the course will be presented. PRACTICALS (1 ECTS) For the practical classes, real computer data analysis exercises will be proposed. These exercises will be guided by the teacher of the course and will be carried out in class.