Examining What It’s Going To Take To Get Real Scalability For Chip-based Decision-making

This paper discusses the need for scalable neuromorphic networks, which are networks of neurons that can be used for machine learning. It proposes a novel wavelength-switched photonic neural network (WS-PNN) system architecture, which has the benefit of flattened scalability and flexibility. It also covers the basics of photonic integrated circuit hardware, which is needed for scalability due to the speed of light. The paper also discusses different layer types and topologies, as well as two types of photonic neurons.