Approximate reservoir computing with a semiconductor laser for reducing energy consumption

Abstract

Photonic reservoir computing is a promising physical machine-learning approach for time-series prediction. Quantization of the reservoir response signal is an important consideration in the implementation of photonic reservoir computing, and the number of quantization bits and sampling frequency need to be optimized to achieve high prediction performance and low energy consumption. However, few studies have investigated the effects of the number of quantization bits and sampling frequency on both prediction performance and energy consumption. In this study, we introduce the concept of approximate reservoir computing with a semiconductor laser by quantizing the reservoir node states and output weights. We numerically evaluate the performance of a chaotic time-series prediction task and estimate the energy consumption per sample using a component-level model. By optimizing the number of quantization bits, the sampling frequency, and the injection current of the semiconductor laser, we achieve a significant reduction in the estimated energy consumption per sample while maintaining prediction performance. We also obtain model-based estimates of the throughput, energy efficiency, and energy per operation of the proposed reservoir-computing system.