Active learning of Neural Network proxies for aerodynamic optimization

Presentation

Many practical continuous minimization problems, such as aerodynamic optimization, are not amenable to gradient-based optimization methods because derivatives can not be computed directly. We recently showed that it is possible to train a Neural Network regressor as a proxy to the numerical simulator and optimise the proxy function via Gradient-Descent.
However, in practice, each datapoint requires an expensive call to a numerical simulator. Therefore, we need to use active learning techniques or reinforcement learning-based strategies to optimally sample the initial dataset and re-use the simulator judiciously during the optimization phase.

Outcomes of the project

An efficient active learning strategy to take the best advantage of a limited number of calls to the simulator before and during the optimization process would have a strong theoretical and industrial impact.

Researched profile
  • Knowledge of Machine Learning and Optimisation Theory
  • Experience using Python
  • Taste for experimentation and/or theory in CS
Gained knowledge
  • Learn how to use correctly a Deep-Learning framework (TensorFlow)
  • Gain expertise in the field of Active Learning
  • Put your feets in an emerging field, at the frontier of machine learning and optimization
Loaction and Dates

Computer Vision Laboratory, EPFL, Lausanne.
12 Weeks or more, anytime.

Contact

Please contact us pierre.baque(at)epfl.ch or edoardo.remelli(at)epfl.ch for any further information.