Brain-inspired AI for Edge Intelligence: a systematic review

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Yingchao, Wang, Meijia, Hao, Zhifeng, Buyya, Rajkumar
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917364646281216
author Cheng, Yingchao
Wang, Meijia
Hao, Zhifeng
Buyya, Rajkumar
author_facet Cheng, Yingchao
Wang, Meijia
Hao, Zhifeng
Buyya, Rajkumar
contents While Spiking Neural Networks (SNNs) promise to circumvent the severe Size, Weight, and Power (SWaP) constraints of edge intelligence, the field currently faces a "Deployment Paradox" where theoretical energy gains are frequently negated by the inefficiencies of mapping asynchronous, event-driven dynamics onto traditional von Neumann substrates. Transcending the reductionism of algorithm-only reviews, this survey adopts a rigorous system-level hardware-software co-design perspective to examine the 2020-2025 trajectory, specifically targeting the "last mile" technologies - from quantization methodologies to hybrid architectures - that translate biological plausibility into silicon reality. We critically dissect the interplay between training complexity (the dichotomy of direct learning vs. conversion), the "memory wall" bottlenecking stateful neuronal updates, and the critical software gap in neuromorphic compilation toolchains. Finally, we envision a roadmap to reconcile the fundamental "Sync-Async Mismatch," proposing the development of a standardized Neuromorphic OS as the foundational layer for realizing a ubiquitous, energy-autonomous Green Cognitive Substrate.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26722
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Brain-inspired AI for Edge Intelligence: a systematic review
Cheng, Yingchao
Wang, Meijia
Hao, Zhifeng
Buyya, Rajkumar
Neural and Evolutionary Computing
Artificial Intelligence
Hardware Architecture
Operating Systems
While Spiking Neural Networks (SNNs) promise to circumvent the severe Size, Weight, and Power (SWaP) constraints of edge intelligence, the field currently faces a "Deployment Paradox" where theoretical energy gains are frequently negated by the inefficiencies of mapping asynchronous, event-driven dynamics onto traditional von Neumann substrates. Transcending the reductionism of algorithm-only reviews, this survey adopts a rigorous system-level hardware-software co-design perspective to examine the 2020-2025 trajectory, specifically targeting the "last mile" technologies - from quantization methodologies to hybrid architectures - that translate biological plausibility into silicon reality. We critically dissect the interplay between training complexity (the dichotomy of direct learning vs. conversion), the "memory wall" bottlenecking stateful neuronal updates, and the critical software gap in neuromorphic compilation toolchains. Finally, we envision a roadmap to reconcile the fundamental "Sync-Async Mismatch," proposing the development of a standardized Neuromorphic OS as the foundational layer for realizing a ubiquitous, energy-autonomous Green Cognitive Substrate.
title Brain-inspired AI for Edge Intelligence: a systematic review
topic Neural and Evolutionary Computing
Artificial Intelligence
Hardware Architecture
Operating Systems
url https://arxiv.org/abs/2603.26722