Integration of Neuromorphic AI in Event-Driven Distributed Digitized Systems: Concepts and Research Directions

Abstract

Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource requirements of digital computing and deep learning are growing exponentially, in an unsustainable manner. One possible way to bridge this gap is the adoption of resource-efficient brain-inspired "neuromorphic" processing and sensing devices, which use event-driven, asynchronous, dynamic neurosynaptic elements with colocated memory for distributed processing and machine learning. However, since neuromorphic systems are fundamentally different from conventional von Neumann computers and clock-driven sensor systems, several challenges are posed to large-scale adoption and integration of neuromorphic devices into the existing distributed digital-computational infrastructure. Here, we describe the current landscape of neuromorphic computing, focusing on characteristics that pose integration challenges. Based on this analysis, we propose a microservice-based framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which provides virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction. We also present concepts that could serve as a basis for the realization of this framework, and identify directions for further research required to enable large-scale system integration of neuromorphic devices.

References in corpus (20)

• Memory and information processing in neuromorphic systems
• Brain-inspired computing: We need a master plan
• Neuromorphic electronic circuits for building autonomous cognitive systems
• SLAYER: Spike Layer Error Reassignment in Time
• BindsNET: A machine learning-oriented spiking neural networks library in Python
• Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System
• Ultra-Low-Power FDSOI Neural Circuits for Extreme-Edge Neuromorphic Intelligence
• Whetstone: A Method for Training Deep Artificial Neural Networks for Binary Communication
• Neurosymbolic AI: The 3rd Wave
• The importance of space and time in neuromorphic cognitive agents
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• Deep Declarative Networks: A New Hope
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision
• Sampling and Reconstruction of Bandlimited Signals with Multi-Channel Time Encoding
• Sub-mW Neuromorphic SNN audio processing applications with Rockpool and Xylo
• Asynchrony Increases Efficiency: Time Encoding of Videos and Low-Rank Signals
• Dimensions of Timescales in Neuromorphic Computing Systems
• FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
• Neuro-symbolic computing with spiking neural networks
• EXODUS: Stable and Efficient Training of Spiking Neural Networks

Cited by in corpus (1)

• Progress in End-to-End Optimization of Detectors for Fundamental Physics with Differentiable Programming