An integrated photonics reservoir computing using chaotic semiconductor laser hybrid with Si3N4 micro-resonator
Lehan Zhao, Yuanyun Wang, Qingsong Bai, Jin Deng, Zihan Shen, Haitang Li, Guang-Qiong Xia, Zheng-Mao Wu, Junbo Yang, Jiagui Wu · 2023
Reservoir computing (RC) is a computational framework for information processing based on neural network. It can be implemented with different physical platforms, principally, electronic architectures and photonic architectures. Photonic RC shows potential path to ultra-fast and efficient processing beyond the traditional Turing-von Neumann computer architecture. Typical photonics RC consider specifically a semiconductor laser (SL) with delayed feedback as reservoir substrate. Basically, the SL is a kind of type B laser, needing enough long delay feedback for the high dimensional chaos generation and for the RC mapping. But on the other hand, long delay feedback leads to the setup big size, being nonconductive of integration implement and stable operation performance in real world. To solve the problem of a huge size, we propose a new photonics RC scheme that using chaotic SL hybrid with Si3N4 micro-resonator, which works as the storage layer and feedback loop. The Si3N4 micro-resonator could help SL producing high-dimensional chaos and reaching high-complexity RC. Meanwhile, the size of Si3N4 micro-resonator is highly compressed at the level of ten micrometers, thereby realizing a size compression of over ten times than that of typical photonics RC setup. In our experiment, we make the free spectrum range (FSR) of micro-resonator is 35GHz, reaching the nonlinear frequency of SL. Then, with careful operation, two-mode mixing chaos can be realized, being very conductive for the photonics RC applications. These results are conducive for the development of on-chip photonic RC.