TY - JOUR

T1 - 2022 roadmap on neuromorphic computing and engineering

AU - Christensen, Dennis V.

AU - Dittmann, Regina

AU - Linares-Barranco, Bernabe

AU - Sebastian, Abu

AU - Le Gallo, Manuel

AU - Redaelli, Andrea

AU - Slesazeck, Stefan

AU - Mikolajick, Thomas

AU - Spiga, Sabina

AU - Menzel, Stephan

AU - Valov, Ilia

AU - Milano, Gianluca

AU - Ricciardi, Carlo

AU - Liang, Shi Jun

AU - Miao, Feng

AU - Lanza, Mario

AU - Quill, Tyler J.

AU - Keene, Scott T.

AU - Salleo, Alberto

AU - Grollier, Julie

AU - Marković, Danijela

AU - Mizrahi, Alice

AU - Yao, Peng

AU - Yang, J. Joshua

AU - Indiveri, Giacomo

AU - Strachan, John Paul

AU - Datta, Suman

AU - Vianello, Elisa

AU - Valentian, Alexandre

AU - Feldmann, Johannes

AU - Li, Xuan

AU - Pernice, Wolfram H.P.

AU - Bhaskaran, Harish

AU - Furber, Steve

AU - Neftci, Emre

AU - Scherr, Franz

AU - Maass, Wolfgang

AU - Ramaswamy, Srikanth

AU - Tapson, Jonathan

AU - Panda, Priyadarshini

AU - Kim, Youngeun

AU - Tanaka, Gouhei

AU - Thorpe, Simon

AU - Bartolozzi, Chiara

AU - Cleland, Thomas A.

AU - Posch, Christoph

AU - Liu, Shih Chii

AU - Panuccio, Gabriella

AU - Mahmud, Mufti

AU - Mazumder, Arnab Neelim

AU - Hosseini, Morteza

AU - Mohsenin, Tinoosh

AU - Donati, Elisa

AU - Tolu, Silvia

AU - Galeazzi, Roberto

AU - Christensen, Martin Ejsing

AU - Holm, Sune

AU - Ielmini, Daniele

AU - Pryds, N.

N1 - Publisher Copyright: © 2022 The Author(s). Published by IOP Publishing Ltd.

PY - 2022

Y1 - 2022

N2 - Modern computation based on von Neumann architecture is now a mature cutting-edge science. In the von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.

AB - Modern computation based on von Neumann architecture is now a mature cutting-edge science. In the von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community.

KW - convolutional neural networks

KW - deep learning

KW - memristor

KW - neuromorphic computation

KW - robotics

KW - self-driving cars

KW - spiking neural networks

U2 - 10.1088/2634-4386/ac4a83

DO - 10.1088/2634-4386/ac4a83

M3 - Journal article

AN - SCOPUS:85148326290

VL - 2

JO - Neuromorphic Computing and Engineering

JF - Neuromorphic Computing and Engineering

SN - 2634-4386

IS - 2

M1 - 022501

ER -