All-optical spiking neurosynaptic networks with self-learning capabilities

Researchers from University of Munster, University of Oxford and University of Exeter report in Nature an all-optical version of a neurosynaptic system, capable of supervised and unsupervised learning. They exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data. This report is also discussed further in a Nature news article highlighting the potential future impact should photonic neural accelerators offering high energy efficiencies eventually emerge. This paper also featured in MPLS news.