Hybrid Convolutional Optoelectronic Reservoir Computing for Image Recognition

Photonic delay-based reservoircomputers (RC) have emerged as an attractive high-speed, low-power alternative to traditional digital hardware for AI. We demonstrate experimentally a novel hybrid RC scheme in which input data is first preprocessed through several convolutional layers, either trained or untrained, digitally to generate novel feature maps. These random feature maps are then processed through an optoelectronic implementation of delay-based RC. Using the MNIST dataset of handwritten digits, experiments of our proposed hybrid scheme achieve classification error of 1.6% using untrained convolutions, and an error of 1.1% using trained convolutions, results comparable to that of state-of-the-art machine learning algorithms. Additionally, our experimental implementation can offer a potential 10x decrease in model training time, compared to that of common digital alternatives.

Automated summary

This article introduces a novel hybrid scheme of photonic delay-based reservoir computers (RC) that preprocess input data through convolutional layers and then process them through an optoelectronic implementation of delay-based RC. Experimental results show that the proposed scheme achieves comparable classification performance to state-of-the-art machine learning algorithms and significantly reduces model training time.