2022 roadmap on neuromorphic computing and engineering

Abstract

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In the Von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The Roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this Roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.

Utility and Feasibility of a Center Surround Event Camera

“…Some event cameras even include activity-driven [23] or sampled [24] intensity values. Resolution and readout bandwidth have increased dramatically, which is great for applications like self-driving cars that must see small objects far away [25].…”

“…However, biological Retinal Ganglion Cell (RGC) spikes are the result of vastly sophisticated computations relevant for survival, and it seems with the drive for more and smaller pixels, event camera design is diverging from biology. With this rich historical background-and with industry occupied with the megapixel DVS race [25]- [27]-it is a good opportunity to revisit the idea of implementing at least a simple antagonistic center surround. The main questions we answer are:…”

Implementing Spiking Neural Networks on Neuromorphic Architectures: A Review

“…Table 1: Capacity of some recent neuromorphic systems [18]. NVM devices present an attractive option for implementing synaptic storage due to their demonstrated potential for low-power multilevel operations and high integration densities [27,28,29,30].…”

Design-Technology Co-Optimization for NVM-based Neuromorphic Processing Elements

“…Neuromorphic computing systems are integrated circuits that implement the architecture of central nervous system in primates [14,22,65]. These systems facilitate energy-efficient computations using Spiking Neural Networks (SNN) [63] for power-constrained embedded devices.…”