Digital neuromorphic technology:current and future prospects  

作　　者：Steve Furber 

机构地区：[1]Department of Computer Science,The University of Manchester,UK

出　　处：《National Science Review》2024年第5期3-4,共2页国家科学评论（英文版）

基　　金：supported by the European Union Flagship Human Brain Project SGA3(H2020945539).

摘　　要：Neuromorphic technology has diversified considerably from its origins in the seminal work by Carver Mead and his group at Caltech in the 1980s[1].That early work focussed on the analogy between the equations describing the flow of ions in biological neurons and the equations describing the flow of carriers in field-effect transistors operating in the subthreshold region.Though research continues into both subthreshold and above-threshold analogue neuromorphic circuits,this is complemented by developments in digital neuromorphic systems that take inspiration from biological neuronal systems at higher levels in their architectures,solving the low-level equations with digital hardware or software rather than by direct circuit-level emulation.

关 键 词：ANALOGY EQUATIONS considerably 

分 类 号：TP333[自动化与计算机技术—计算机系统结构]