Silicon Photonic Neural Networks and Applications

Neuromorphic photonic processors promise orders of magnitude improvements in both speed and energy efficiency over purely digital electronic approaches. We will provide an overview of neuromorphic photonic systems and their application to machine learning and specifically deep learning inference with a hybrid digital electronics and analog photonics architecture based on silicon photonics. We will discuss scalability in the context of designing a full-scale neuromorphic photonic processing system, considering aspects such as signal integrity, noise, and hardware fabrication platforms.