EDITORIAL article
Front. Neurosci.
Sec. Neuromorphic Engineering
This article is part of the Research TopicAlgorithm-Hardware Co-Optimization in Neuromorphic Computing for Efficient AIView all 7 articles
Editorial: Algorithm-Hardware Co-Optimization in Neuromorphic Computing for Efficient AI
Provisionally accepted
- 1University of Twente, Enschede, Netherlands
- 2Instituto de Microelectronica de Sevilla, Seville, Spain
- 3Technische Universiteit Delft, Delft, Netherlands
- 4Innatera, Delft, Netherlands
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Neuromorphic computing holds the promise of sustainable AI by combining brain-inspired models 4 with event-driven, massively parallel hardware. However, a central question remains: when and how 5 do neuromorphic systems convert their architectural advantages into effective end-to-end efficiency 6 for real-world tasks? This Research Topic presents six contributions that address this question from 7 various perspectives. Specifically, it explores training methods that minimize timesteps and memory 8 usage, hardware-aware algorithms and quantization, emulation techniques that mitigate risks associated 9 with analog platforms, and mapping and scheduling strategies that enhance utilization on many-core 10 neuromorphic chips. 11 We are pleased to present a series of innovative research articles in this field that introduce the following
Keywords: neuromorphic computing, Algorithm-hardware co-optimization, Spiking neural networks (SNNs), Temporal efficiency / timestep reduction, Hardware-aware mapping and learning
Received: 14 Nov 2025; Accepted: 24 Nov 2025.
Copyright: © 2025 Yousefzadeh, Patiño-Saucedo, Croon and Sifalakis. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Amirreza Yousefzadeh
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.