https://doi.org/10.1051/epjconf/202328713010
Experimental Investigation of Time-Stretch-Based Reservoir Computing with an Optical Input Mask
1 School of Engineering, University of Kent, Canterbury CT2 7NT, United Kingdom.
2 School of Automation, Guangdong University of Technology, Guangzhou, China.
* Corresponding author: C.Wang@kent.ac.uk
Published online: 18 October 2023
In this paper, we experimentally demonstrated a novel all-optical reservoir computer with an all optical input mask. The combination of the binary random masks and the time-stretched ultrashort pulses has increased the system’s classification performance. Compared with the traditional digital masks, this method shows superior classification performance in spoken-digit classification tasks and eliminates the need for high-speed modulation for digital masks.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
