Neuromorphic Wireless Split Computing with Multi-Level Spikes

2024-11-07

arXiv.org

AI Summary

In neuromorphic computing, achieving both high transmission efficiency and inference accuracy for multi-level spike signals over wireless hierarchical architectures remains challenging. Method: This paper proposes a split-computing architecture for spiking neural networks (SNNs) tailored to wireless environments. It innovatively co-optimizes multi-level spike encoding with OFDM-based wireless interfaces, designing an analog/digital hybrid modulation scheme specifically suited for neuromorphic communication. Contribution/Results: Evaluated via SDR experiments and simulations, the approach demonstrates that multi-level spikes significantly improve inference accuracy; dynamically selecting the optimal spike payload bit-width per channel condition reduces communication overhead by 40% while preserving ≥98% of the original accuracy. This work presents the first joint optimization of spike encoding, wireless physical-layer design, and SNN computation—establishing a novel paradigm for large-scale, low-power edge intelligence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Inspired by biological processes, neuromorphic computing utilizes spiking neural networks (SNNs) to perform inference tasks, offering significant efficiency gains for workloads involving sequential data. Recent advances in hardware and software have demonstrated that embedding a few bits of payload in each spike exchanged between the spiking neurons can further enhance inference accuracy. In a split computing architecture, where the SNN is divided across two separate devices, the device storing the first layers must share information about the spikes generated by the local output neurons with the other device. Consequently, the advantages of multi-level spikes must be balanced against the challenges of transmitting additional bits between the two devices. This paper addresses these challenges by investigating a wireless neuromorphic split computing architecture employing multi-level SNNs. For this system, we present the design of digital and analog modulation schemes optimized for an orthogonal frequency division multiplexing (OFDM) radio interface. Simulation and experimental results using software-defined radios provide insights into the performance gains of multi-level SNN models and the optimal payload size as a function of the quality of the connection between a transmitter and receiver.

Problem

• Neuromorphic Computing
• Hierarchical Wireless Architecture
• Optimization of Information Transmission

Innovation

• Neuromorphic Hierarchical Computing
• Multi-level Pulse Transmission
• Dynamic Adjustment Strategy