The Universitat de Barcelona Institute of Complex Systems (UBICS) celebrates its annual meeting.
Jose M.G. Vilar (Biofisika Institute (CSIC-UPV/EHU) University of the Basque Country)
I will comment on the approach and methodology I used in winning the European Union Big Data Technologies Horizon Prize on data-driven prediction of electricity grid traffic. The methodology relies on identifying typical short-term recurrent fluctuations, which is subsequently refined through a regression-of-fluctuations approach. I will also emphasize the key points and strategic considerations that led to selecting or discarding different methodological aspects. The criteria include adaptability to changing conditions, reliability with outliers and missing data, robustness to noise, and efficiency in implementation.
Roger Guimerà, ICREA & Universitat Rovira i Virgili
Since the scientific revolution, interpretable closed-form mathematical models have been instrumental for advancing our understanding of the world. Think, for example, of Newton’s law of gravitation, and how it has enabled us to predict astronomical phenomena with great accuracy and to gain deep insights about seemingly unrelated physical phenomena. With the data revolution, we may now be in a position to uncover new mathematical models for many systems, from physics and chemistry to the social sciences. However, to deal with increasing amounts of data, we need approaches that are able to extract these models automatically, without supervision, and with guarantees of asymptotically finding the correct model. In this talk I will review standard machine learning approaches and discuss their limitations in terms of getting interpretable models. Then, I will present a Bayesian "machine scientist" that deals rigorously with model plausibilities and also explores systematically the space of models, using the analogy between Bayesian inference, information theory, and statistical mechanics. The machine scientist is able to obtain closed-form mathematical models from data, and to make out-of-sample predictions that are more accurate than those of standard machine learning approaches.
Lecturers: Marco Dentz and Juan Hidalgo (IDAEA-CSIC)
Postgraduate course addressed to physicists, chemists and engineers, organized in five 2-hour sessions:
- April 29: Introduction to transport in heterogeneous media.
- May 13: Langevin and Fokker-Planck equations
- May 20: Dispersion
- June 3: Continuous time random walks
- July 1: Trapping models
All sessions will take place on Monday, from 11 to 13 h, at room 3.20 (3rd floor of Physics UB, new building, campus Sud de Pedralbes).