About:

This workshop focused on the interplay between model uncertainty and risk in machine learning and addressed the main developments towards understanding why deep learning works. The workshop looked at how to analyse learning efficiency of deep learning algorithms, convergence and their robustness under input perturbations using tools from the theory of dynamical systems, mean-field games and ODEs. This workshop identifed the crucial ingredients of a systematic and rigorous framework, and optimization methods for designing deep learning architectures with high approximation capacity and efficient training rates, critically studied their performance, and predicted their behaviour under different conditions with provable guarantees on the estimates.

The workshop engaged with industry partners to inform a dialogue towards developing comprehensive  risk management  frameworks  with  ML-based algorithms with an outlook for long-term collaborative and impactful research.

By bringing together international and UK experts in the area of random and stochastic dynamical systems, machine learning and deep learning, and mean-field theory, this workshop fostered a dialogue between these groups and provided a forum for collaborations and cross-fertilization.