Chunxu Ding, Rongjun Shao, Jingwei Li, Yuan Qu, Linxian Liu, Qiaozhi He, Xunbin Wei, Jiamiao Yang, "Optoelectronic reservoir computing based on complex-value encoding," Adv. Photon. Nexus 3, 066006 (2024)

Search by keywords or author
- Advanced Photonics Nexus
- Vol. 3, Issue 6, 066006 (2024)

Fig. 1. Principle of CE-ORC. The complex-valued encoding strategy converts the input state defined in the real space, with the previous state , to a complex optical field. The scattering medium as the reservoir transforms this field to the current state that is captured by the detector. Based on the captured image, a trained program generates the current output .

Fig. 2. Experimental setup and characterization of CE-ORC system. (a) Schematic illustration and physical demonstration of the CE-ORC implementation. M, mirror; and , lenses; PF, pinhole filter; SM, scattering medium. (b) CE-ORC processing unit and dedicated FPGA board. (c) Distance matrix of the CE-ORC system with the encoding dimension of 10. (d) Correlation matrix of the responses in different ORC systems.
![The horizontal coordinate representing time has been normalized with respect to the Lyapunov exponent Λmax. (a) Example of free-running prediction made by CE-ORC at optimal configuration (si=0.95 and sr=0.9). (b) Comparison of NMSE in the free-running predictions given by the conventional basket-encoding ORC, and CE-ORC with different configurations of the scale factors. (c) Example of one-step prediction made by CE-ORC at si=0.95 and sr =0.9. (d) Comparison of errors in the one-step predictions given by the conventional basket-encoding ORC and CE-ORC. Note: Free-running prediction [(a), (b)] and one-step prediction [(c), (d)] are different prediction modes and should not be directly compared.](/Images/icon/loading.gif)
Fig. 3. The horizontal coordinate representing time has been normalized with respect to the Lyapunov exponent . (a) Example of free-running prediction made by CE-ORC at optimal configuration ( and ). (b) Comparison of NMSE in the free-running predictions given by the conventional basket-encoding ORC, and CE-ORC with different configurations of the scale factors. (c) Example of one-step prediction made by CE-ORC at and . (d) Comparison of errors in the one-step predictions given by the conventional basket-encoding ORC and CE-ORC. Note: Free-running prediction [(a), (b)] and one-step prediction [(c), (d)] are different prediction modes and should not be directly compared.

Fig. 4. Test of CE-ORC for weather forecast. (a) Predictions of temperature made by the CE-ORC and conventional basket-encoding ORC in the free-running prediction mode. (b) Predictions of humidity made by the CE-ORC and conventional basket-encoding ORC in the free-running prediction mode. (c) Predictions of temperature made by the CE-ORC in the one-step prediction mode. (d) Errors in the predictions of humidity made by the CE-ORC in the one-step prediction mode.

Set citation alerts for the article
Please enter your email address