Physics Based Machine Learning. Machine learning artificial intelligence in the quantum domain arXiv170902779 by Vedran Dunjko Hans J. Hypothesis space could be quite large even for a fairly simple algorithm. Integrating Machine Learning with Physics-Based Modeling. While certain methods like Random Forests are amenable to preserving physical features deep learning methods like neural networks tend to obscure the reasoning behind the response.
Molecular dynamics and moment closure of kinetic equations are used as examples to illustrate the main issues dis-. However many issues need to be addressed before this becomes a reality. Machine learning methods learn map between inputs and POD coefficients. This does not mean that machine learning is useless for any problem that can be described using physics-based modeling. The ability of ML models to learn from experience means they can also learn physics. While certain methods like Random Forests are amenable to preserving physical features deep learning methods like neural networks tend to obscure the reasoning behind the response.
However these require a large amount of computational power and can still take days.
Particular solutions enforce boundary conditions and other physical solution features. While certain methods like Random Forests are amenable to preserving physical features deep learning methods like neural networks tend to obscure the reasoning behind the response. New approach for physics-based machine learning using POD expansions. This article focuses on one particular issue of broad interest. On the contrary combining physics with machine learning in a hybrid modeling scheme is a very exciting prospect. Machine learning artificial intelligence in the quantum domain arXiv170902779 by Vedran Dunjko Hans J.