Search Results for author:
Found 2 papers, 0 papers with code
Curriculum learning for data-driven modeling of dynamical systems
Based on that, we consider entropy as a metric of complexity of the dataset; we show how an informed design of the training set based on the analysis of the entropy significantly improves the resulting models in terms of generalizability, and provide insights on the amount and the choice of data required for an effective data-driven modeling.
Compressibility, laws of nature, initial conditions and complexity
In particular we discuss the subtle conceptual topic of the initial conditions of phenomena which are generally incompressible.
Statistical Mechanics Chaotic Dynamics History and Philosophy of Physics
