Harnessing Optoelectronic Noises in a Photonic Generative Network

Abstract

Integrated optoelectronics is emerging as a promising platform of neural network accelerator, which affords efficient in-memory computing and high bandwidth interconnectivity. The inherent optoelectronic noises, however, make the photonic systems error-prone in practice. It is thus imperative to devise strategies to mitigate and, if possible, harness noises in photonic computing systems. Here, we demonstrate a photonic generative network as a part of a generative adversarial network (GAN). This network is implemented with a photonic core consisting of an array of four programable phase-change memory cells to perform 4-elements vector-vector dot multiplication. We demonstrate that the GAN can generate a handwritten number ("7") in experiments and full ten digits in simulation. We realize an optical random number generator derived from the amplified spontaneous emission noise, apply noise-aware training by injecting additional noise and demonstrate the network's resilience to hardware non-idealities. Our results suggest the resilience and potential of more complex photonic generative networks based on large-scale, realistic photonic hardware.