Efficient Reservoir Computing using Field Programmable Gate Array and Electro-optic Modulation

TL;DR

This paper presents a hybrid reservoir computing system combining an electro-optic modulator and FPGA, demonstrating high accuracy and versatility in benchmark tests, suitable for real-time applications like forecasting and recognition.

Contribution

The work introduces a novel hybrid electro-optic and FPGA-based reservoir computing system with digital delay lines and filters, enabling flexible dynamics and large-scale node connectivity.

Findings

Achieved low NRMSE of 0.142 and 0.148 in NARMA-10 predictions.

Demonstrated NMSE of 6.73x10^-3 in Santa Fe laser data prediction.

Attained 0.34% word error rate in spoken digit recognition.

Abstract

We experimentally demonstrate a hybrid reservoir computing system consisting of an electro-optic modulator and field programmable gate array (FPGA). It implements delay lines and filters digitally for flexible dynamics and high connectivity, while supporting a large number of reservoir nodes. To evaluate the system's performance and versatility, three benchmark tests are performed. The first is the 10th order Nonlinear Auto-Regressive Moving Average test (NARMA-10), where the predictions of 1000 and 25,000 steps yield impressively low normalized root mean square errors (NRMSE's) of 0.142 and 0.148, respectively. Such accurate predictions over into the far future speak to its capability of large sample size processing, as enabled by the present hybrid design. The second is the Santa Fe laser data prediction, where a normalized mean square error (NMSE) of 6.73x10-3 is demonstrated. The third is the isolate spoken digit recognition, with a word error rate close to 0.34%. Accurate, versatile, flexibly reconfigurable, and capable of long-term prediction, this reservoir computing system could find a wealth of impactful applications in real-time information processing, weather forecasting, and financial analysis.