Deep learning for new insights into ultrafast dynamics and extreme events in nonlinear fibre optics

摘要: Although the successes of artificial intelligence in areas such as automatic translation are well known, application powerful techniques deep learning to current optics research is at a comparatively early stage. However, an area with particular promise for accelerate both basic science and applications ultrafast optics, where nonlinear light-matter interactions lead highly complex dynamics, including emergence extreme events. In field fibre we have recently reported number results that shown how can augment existing experimental provide new theoretical insights into underlying physics. The objective this paper review selection our work area.