Optical seminar | 13 July 2022

Fiber mode-locked lasers are essential tools in many areas of photonics, including material processing telecommunications and biological imaging. Although some ultrafast sources are based on relatively simple designs, the operation of many important laser systems is in fact very complex, with dynamic pulse shaping determined by the interplay between a range of nonlinear, dispersive and dissipative effects.
In this context, artificial intelligence (AI) algorithms offer a nonlinearity-friendly, efficient and flexible alternative to the classical control techniques. AI-based control methods have been studied extensively and have proved indispensable in systems where knowledge of the underlying mathematical models is limited or absent.
This talk is devoted to AI algorithms have been recently applied to mode‑locked fiber lasers with the special focus on three key areas: self‑starting, system optimization and characterization.

Main paper/arXiv, related to the seminar, and other references

1) Genty, G., Salmela, L., Dudley, J. M., Brunner, D., Kokhanovskiy, A., Kobtsev, S., & Turitsyn, S. K. (2021). Machine learning and applications in ultrafast photonics. Nature Photonics, 15(2), 91-101.
2) Kokhanovskiy, A., Kuprikov, E., Bednyakova, A., Popkov, I., Smirnov, S., & Turitsyn, S. (2021). Inverse design of mode-locked fiber laser by particle swarm optimization algorithm. Scientific reports, 11(1), 1-9.
3) Kokhanovskiy, A., Bednyakova, A., Kuprikov, E., Ivanenko, A., Dyatlov, M., Lotkov, D., ... & Turitsyn, S. (2019). Machine learning-based pulse characterization in figure-eight mode-locked lasers. Optics Letters, 44(13), 3410-3413.
4) Kuprikov, E., Kokhanovskiy, A., Serebrennikov, K., & Turitsyn, S. (2022). Deep reinforcement learning for self-tuning laser source of dissipative solitons. Scientific Reports, 12(1), 1-9.
5) Kokhanovskiy, A., Ivanenko, A., Kobtsev, S., Smirnov, S., & Turitsyn, S. (2019). Machine learning methods for control of fibre lasers with double gain nonlinear loop mirror. Scientific reports, 9(1), 1-7.