Physics-Informed Learning
A machine learning approach that embeds known physical constraints, such as the monotonic decrease of fidelity with decoherence and probability normalization, into model structure or loss functions, with the aim of improving extrapolation and generalization when training data are limited.
Timeline (last 90 days)
Physics-informed learning embeds known physical constraints into the model structure or loss function, with the aim of improving extrapolation and generalization when training data are limited.
There is disagreement regarding the generalization ability of learned surrogate models: some views hold that learned models may struggle to generalize to unseen network topologies; others emphasize that generalization can be improved through physics-informed learning.
All Facts (2)
Physics-informed learning embeds known physical constraints into the model structure or loss function, with the aim of improving extrapolation and generalization when training data are limited.
50%UnverifiedThere is disagreement regarding the generalization ability of learned surrogate models: some views hold that learned models may struggle to generalize to unseen network topologies; others emphasize that generalization can be improved through physics-informed learning.
50%