Photonic Reservoir Computing System for Pattern Recognition Based on an Array of Four Distributed Feedback Lasers

Reservoir computing (RC), especially photonic RC based on a single semiconductor laser with a feedback loop, as a method of machine learning, shows excellent performance in time series prediction and classification tasks. The faster the processing speed, the shorter the feedback loop should be employed. However, the performance of the system is not ideal enough due to the limited reservoir nodes caused by the short feedback loop. To overcome this drawback, it is necessary and challenging to develop integrated photonic RC. In this paper, we propose an integrated neuromorphic photonic time-delayed RC scheme based on an array of four distributed feedback lasers (F-DFBs) with optical feedback and injection. Here, we investigate the feasibility of using larger laser arrays and shorter external feedback cavities to provide the RC system with more virtual nodes at the same processing speed, enabling it to handle more complex tasks. Additionally, we compare the performance of the systems with a single DFB (the S-DFB RC) and the F-DFBs RC through simulations and experiments involving iris recognition tasks. Furthermore, the minimum symbol error rate values can reach 0.052 in experiments (and 0 in simulations).