发表机构
Saitama University; Kyushu University（埼玉大学; 九州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于半导体激光器的近似储层计算，通过量化储层节点状态幅度和输出权重，优化量化位数、采样频率和注入电流，在混沌时间序列预测中显著降低能耗并保持性能。
AI 中文摘要
光子储层计算是一种用于预测时间序列数据的很有前景的物理机器学习技术。光子储层计算的实现需要对储层的响应信号进行量化，并且需要优化量化位数和采样频率以实现高性能和低能耗。然而，很少有研究探讨比特量化和采样频率的影响。在本研究中，我们通过对储层中的节点状态幅度和输出权重进行量化，引入了一种基于半导体激光器的近似储层计算概念。我们评估了混沌时间序列预测任务的性能和每个样本的能耗。通过优化量化位数、采样频率和半导体激光器的注入电流，我们在保持预测性能的同时，显著降低了能耗。
英文摘要
Photonic reservoir computing is a promising physical machine-learning technique for predicting time-series data. The quantization of the response signal from the reservoir is required for the implementation of photonic reservoir computing, and the number of quantization bits and sampling frequency need to be optimized to achieve high performance and low energy consumption. However, few studies have been reported to investigate the effect of bit quantization and sampling frequency. In this study, we introduce a concept of approximate reservoir computing with a semiconductor laser by quantizing the amplitude of node states in the reservoir and output weights. We evaluate the performance of a chaotic time-series prediction task and energy consumption per sample. We achieve significant reduction of energy consumption by optimizing the number of quantization bits, the sampling frequency, and the injection current of the semiconductor laser, while maintaining the prediction performance.
Comments9 pages, 10 figures, 3 tables
