Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization

TL;DR

NeuEdge is a framework that combines adaptive spiking neural networks with hardware-aware optimization to enable ultra-low-power, real-time edge AI applications with high accuracy and energy efficiency.

Contribution

It introduces a novel adaptive SNN model with a combined rate and spike-timing coding scheme and hardware-aware training for efficient edge deployment.

Findings

Achieves 91-96% accuracy on vision and audio benchmarks.

Provides up to 2.3 ms inference latency on edge hardware.

Attains 847 GOp/s/W energy efficiency.

Abstract

Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neural networks (SNNs) offers an attractive path, but practical deployment on resource-constrained devices is limited by training difficulty, hardware-mapping overheads, and sensitivity to temporal dynamics. We present NeuEdge, a framework that combines adaptive SNN models with hardware-aware optimization for edge deployment. NeuEdge uses a temporal coding scheme that blends rate and spike-timing patterns to reduce spike activity while preserving accuracy, and a hardware-aware training procedure that co-optimizes network structure and on-chip placement to improve utilization on neuromorphic processors. An adaptive threshold mechanism adjusts neuron excitability from input statistics, reducing energy consumption without degrading performance. Across standard vision and audio benchmarks, NeuEdge achieves 91-96% accuracy with up to 2.3 ms inference latency on edge hardware and an estimated 847 GOp/s/W energy efficiency. A case study on an autonomous-drone workload shows up to 312x energy savings relative to conventional deep neural networks while maintaining real-time operation.