一种新型信息处理器件:神经形态器件
A new type of information processor device:neuromorphic device
刘逸龙 1李晖 1苏琳琳 2李欣蔚 1杨成东1
作者信息
- 1. 无锡学院电子信息工程学院,江苏无锡 214105;南京信息工程大学电子与信息工程学院,江苏南京 210044
- 2. 无锡学院电子信息工程学院,江苏无锡 214105
- 折叠
摘要
人工智能时代呈现指数增长的待处理数据量对计算机能效提出了更高的要求.因此,在后摩尔时代显然迫切需要开发新型的计算机技术来应对这种挑战.受人脑并行运算架构的启发,模拟突触器件基于"存算一体"架构被认为是突破传统冯·诺依曼瓶颈的有效技术.本文着重梳理了神经形态器件的忆阻机制,按照编程方式对近期突触器件的相关工作开展了分类解读,并结合器件特性介绍了它们在感知模拟等方面的潜在应用.最后,总结了当前神经形态器件所面临的关键技术挑战,并对其未来的发展前景进行了展望.
Abstract
The exponentially increasing pending information volumes in the era of artificial intelligence re-quire digital computer with higher energy efficiency.Thus,it is urgent to develop new computer technol-ogies to address this challenge in the post Moore era.Inspired by the parallel brain's computing architec-ture,synaptic analogues based on the integrated storage and computing architecture is considered as an effective technology to solve the traditional von Neumann bottleneck.Our article highlights the memris-tive mechanism of neuromorphic devices,and also categorizes and interprets recent research works on synaptic devices according to programming modes.Besides,based on device properties makes a introduc-tion of their potential applications in perceptual simulation or other aspects.Finally,the key technical challenges faced by current neuromorphic devices are summarized,and their future development pros-pects are prospected.
关键词
神经形态器件/人工突触/忆阻器/晶体管Key words
neuromorphic device/artificial synapse/memristor/transistor引用本文复制引用
基金项目
国家自然科学基金(62106111)
无锡学院引进人才科研启动项目(2021r011)
无锡学院引进人才科研启动项目(2021r012)
出版年
2024
NETL
NSTL
万方数据