4 papers
Reliable Statistical Guarantees for Conformal Predictors with Small Datasets
Miguel Sánchez-DomÃnguez, Lucas Lacasa, Javier de Vicente +2
Surrogate models (including deep neural networks and other machine learning algorithms in supervised learning) are capable of approximating arbitrarily complex, high-dimensional in…
A Certifiable Machine Learning-Based Pipeline to Predict Fatigue Life of Aircraft Structures
Ãngel Ladrón, Miguel Sánchez-DomÃnguez, Javier Rozalén +5
Fatigue life prediction is essential in both the design and operational phases of any aircraft, and in this sense safety in the aerospace industry requires early detection of fatig…
A novel pointing technique for the enhancement of Tropospheric Delay Calibration System performances
David Bernacchia, Riccardo Lasagni Manghi, Marco Zannoni +5
The beam-crossing is a novel technique aimed at reducing residual tropospheric Doppler noise for microwave radiometer calibrations. In this work, we report the findings of the firs…
Towards certification: A complete statistical validation pipeline for supervised learning in industry
Lucas Lacasa, Abel Pardo, Pablo Arbelo +8
Methods of Machine and Deep Learning are gradually being integrated into industrial operations, albeit at different speeds for different types of industries. The aerospace and aero…