Transfer learning nonlinear plasma dynamic transitions in low dimensional embeddings via deep neural networks

Today's article comes from the journal of Machine Learning Science and Technology. The authors are Bai et al., from Lawrence Berkeley National Laboratory. This paper lies at the intersection of nuclear fusion and deep learning. The authors show us how transfer learning can be used to help a model better understand sudden changes in the physical dynamics of an experiment.

DOI: 10.1088/2632-2153/adca83