Curriculum learning for data-driven modeling of dynamical systems. (arXiv:2112.08458v3 [cs.LG] UPDATED)

The reliable prediction of the temporal behavior of complex systems is key in
numerous scientific fields. This strong interest is however hindered by
modeling issues: often, the governing equations describing the physics of the
system are not accessible or, when known, their solution might require a
computational time incompatible with the prediction time constraints. Not
surprisingly, approximating complex systems in a generic functional format and
informing it ex-nihilo from available observations has become common practice
in the age of machine …

arxiv curriculum curriculum learning data data-driven modeling systems