Parallel neuromorphic computing on space and wavelength division multiplexed photonic processor

Analog photonic processing is one of the attractive computation engines for machine learning. Here, we show recent progress on scaling up analog photonic platforms including a large-scale WDM-based matrix-vector processor and onchip photonic linear processor, as well as their application to reservoir computing and hardware-oriented training. Our approach scales up the photonic analog processing towards the fundamental Nyquist limit.