TY - JOUR
T1 - Roadmap on emerging hardware and technology for machine learning
AU - Berggren, Karl
AU - Xia, Qiangfei
AU - Likharev, Konstantin K.
AU - Strukov, Dmitri B.
AU - Jiang, Hao
AU - Mikolajick, Thomas
AU - Querlioz, Damien
AU - Salinga, Martin
AU - Erickson, John R.
AU - Pi, Shuang
AU - Xiong, Feng
AU - Lin, Peng
AU - Li, Can
AU - Chen, Yu
AU - Xiong, Shisheng
AU - Hoskins, Brian D.
AU - Daniels, Matthew W.
AU - Madhavan, Advait
AU - Liddle, James A.
AU - McClelland, Jabez J.
AU - Yang, Yuchao
AU - Rupp, Jennifer
AU - Nonnenmann, Stephen S.
AU - Cheng, Kwang Ting
AU - Gong, Nanbo
AU - Lastras-Montaño, Miguel Angel
AU - Talin, A. Alec
AU - Salleo, Alberto
AU - Shastri, Bhavin J.
AU - De Lima, Thomas Ferreira
AU - Prucnal, Paul
AU - Tait, Alexander N.
AU - Shen, Yichen
AU - Meng, Huaiyu
AU - Roques-Carmes, Charles
AU - Cheng, Zengguang
AU - Bhaskaran, Harish
AU - Jariwala, Deep
AU - Wang, Han
AU - Shainline, Jeffrey M.
AU - Segall, Kenneth
AU - Yang, J. Joshua
AU - Roy, Kaushik
AU - Datta, Suman
AU - Raychowdhury, Arijit
N1 - Publisher Copyright:
© 2020 IOP Publishing Ltd.
PY - 2020/10/19
Y1 - 2020/10/19
N2 - Recent progress in artificial intelligence is largely attributed to the rapid development of machine learning, especially in the algorithm and neural network models. However, it is the performance of the hardware, in particular the energy efficiency of a computing system that sets the fundamental limit of the capability of machine learning. Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic computing. A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency. Building such a system, nevertheless, faces a number of challenges, ranging from materials selection, device optimization, circuit fabrication and system integration, to name a few. The aim of this Roadmap is to present a snapshot of emerging hardware technologies that are potentially beneficial for machine learning, providing the Nanotechnology readers with a perspective of challenges and opportunities in this burgeoning field.
AB - Recent progress in artificial intelligence is largely attributed to the rapid development of machine learning, especially in the algorithm and neural network models. However, it is the performance of the hardware, in particular the energy efficiency of a computing system that sets the fundamental limit of the capability of machine learning. Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic computing. A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency. Building such a system, nevertheless, faces a number of challenges, ranging from materials selection, device optimization, circuit fabrication and system integration, to name a few. The aim of this Roadmap is to present a snapshot of emerging hardware technologies that are potentially beneficial for machine learning, providing the Nanotechnology readers with a perspective of challenges and opportunities in this burgeoning field.
KW - Artificial intelligence
KW - Hardware technologies
KW - Machine learning
KW - Neural network models
KW - Neuromorphic computing
UR - http://www.scopus.com/inward/record.url?scp=85094219964&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094219964&partnerID=8YFLogxK
U2 - 10.1088/1361-6528/aba70f
DO - 10.1088/1361-6528/aba70f
M3 - Article
C2 - 32679577
AN - SCOPUS:85094219964
SN - 0957-4484
VL - 32
JO - Nanotechnology
JF - Nanotechnology
IS - 1
M1 - 012002
ER -