Kavli Affiliate: Eliska Greplova
| First 5 Authors: D. O. Oriekhov, D. O. Oriekhov, , ,
| Summary:
Much attention has been devoted to the use of machine learning to approximate
physical concepts. Yet, due to challenges in interpretability of machine
learning techniques, the question of what physics machine learning models are
able to learn remains open. Here we bridge the concept a physical quantity and
its machine learning approximation in the context of the original application
of neural networks in physics: topological phase classification. We construct a
hybrid tensor-neural network object that exactly expresses real space
topological invariant and rigorously assess its trainability and
generalization. Specifically, we benchmark the accuracy and trainability of a
tensor-neural network to multiple types of neural networks, thus exemplifying
the differences in trainability and representational power. Our work highlights
the challenges in learning topological invariants and constitutes a stepping
stone towards more accurate and better generalizable machine learning
representations in condensed matter physics.
| Search Query: ArXiv Query: search_query=au:”Eliska Greplova”&id_list=&start=0&max_results=3