NCE特刊征稿|聚焦专注于脑启发电子的自适应材料和器件
特刊详情
客座编辑
- Adnan Mehonic,英国伦敦大学学院
- Erika Covi,德国NaMLab gGmbH
- Giuliana Di Martino,英国剑桥大学
- Ignasi Fina,西班牙巴塞罗那自治大学材料研究所
- Veeresh Deshpande,德国亥姆霍兹联合会柏林能源与材料研究中心
主题范围
Over the last decade, hardware dedicated to Machine Learning (ML) and Artificial Intelligence (AI) has catalysed significant algorithmic advancements and broadening of application scope. Current hardware design aims to mitigate von Neumann system limitations, notably the costly data transfers between physically remote memory and compute units, which are especially problematic for data-centric ML applications. Yet, current hardware solutions, optimised for parallel processing and memory bandwidth, still lean on digital CMOS technology and traditional von Neumann architecture. As Moore’s Law is slowing down and computing demands for ML applications are increasing with unprecedented trends, the need for alternatives to CMOS technologies and innovative architectural strategies becomes crucial. Neuromorphic engineering is one such approach, being inspired by the working principles of the biological brains and systems with the aim to come closer to their incredible efficiency.
This collection offers the latest research on adaptive materials, devices, and systems exhibiting specific brain-inspired functions in a compact, energy-efficient way. This covers the emulation of synapses, neurons and associated systems, as well as concepts such as in-memory computing. Beyond electrical operations, the collection examines device interaction with non-electric stimuli like light and magnetic fields, exploring the potential of integrated sensor/processing/memory units. We anticipate this collection will serve a diverse scientific community, including solid-state physicists, material scientists, chemists, electrical engineers, neuromorphic computing experts, computational neuroscientists, and computer scientists.
投稿流程
特刊文章与NCE期刊常规文章遵循相同的审稿流程和内容标准,并采用同样的投稿模式。
有关准备文章及投稿的详细信息,可以参阅IOPscience页面的作者指南。
作者可登入期刊主页进行在线投稿,先选择“文章类型”,然后在“选择特刊”的下拉框中选择“Focus on Adaptive Materials and Devices for Brain-Inspired Electronics”。
期刊介绍
- 2023年影响因子:5.8 Citescore: 5.9
- Neuromorphic Computing and Engineering(NCE)是一本涵盖多个学科领域、采用开放获取(OA)形式出版的期刊。NCE期刊将神经形态系统的硬件和计算方面结合在一起,读者群覆盖工程、材料科学、物理、化学、生物学、神经科学和计算机科学等领域,跨越学术界和产业界的各个群体。在NCE期刊上发表的研究需针对神经形态系统和人工神经网络领域做出及时而重要的贡献。