Artigo
Acesso aberto
Revisado por pares
Teaching a Neural Network the Hard Way
2021; American Physical Society; Volume: 14; Linguagem: Inglês
10.1103/physics.14.s25
ISSN1943-2879
Autores Tópico(s)Gaussian Processes and Bayesian Inference
ResumoA neural network can be made to produce more reliable predictions of nonlinear systems if it is created with conservation laws built in.
Referência(s)