Using decision tree regression for self-tuning mode-locked lasers: an alternative objective function approach

This study proposes an adaptive control and self-tuning algorithm for mode-locked fiber lasers. The algorithm has three main stages: the birefringence estimation, maximum seeking, and adaptive control. The cavity birefringence is recognized by a decision tree regressor. The optimal position of the polarizer is detected by a maximum seeking algorithm, which involves a novel, to our knowledge, objective function. Thus, the maximal nonlinear polarization rotation is detected by an alternative approach. The adaptive control of the fiber-laser is achieved by combining the birefringence estimation and maximum seeking algorithms, and it is demonstrated that the proposed methodology can keep the fiber-laser mode-locked under varied conditions of cavity birefringence. It is noted that the proposed adaptive control and self-tuning algorithm is equation-free and can be applied to different configurations of mode-locked fiber lasers.