Deep learning and high harmonic generation
share
For the high harmonic generation problem, we trained deep convolutional neural networks to predict time-dependent dipole moments and spectra based on sets of randomly generated parameters (laser pulse intensity, internuclear distance, and molecules orientation). We also taught neural networks to solve the inverse problem - to determine parameters based on spectra or dipole moment data. The latter datasets can also be used to classify molecules by type: di- or triatomic, symmetric or asymmetric, wherein we can even rely on fairly simple fully connected neural networks.
READ FULL TEXT