Paper
16 September 2019 Spin based neuromorphic computing
Author Affiliations +
Abstract
The growth in number of transistors on a semiconductor chip has followed the Moore's law over the years and simultaneously, the size of transistor has reached equivalent to atomic size. Hence, a novel approach is needed for replacement in CMOS technology. The existing technologies are unable to meet the complex computing challenges due to their inability of inherent parallel processing and adaptability. Hence, there is a need of unconventional methodologies such as quantum computing and neuromorphic computing; and technologies like spintronics to support the realization of these methodologies. Skyrmions are the primary components of skyrmionics, the next generation of spintronics. These are the promising candidates for neuromorphic computing due to their significant features such as topological stability, low driving current density and nanoscale size. In this paper, spintronics based neuromorphic computing has been reviewed and the performance is evaluated in comparison to conventional techniques.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Namita Bindal, Anant Kulkarni, Gyanendra Singh, and Brajesh Kumar Kaushik "Spin based neuromorphic computing", Proc. SPIE 11090, Spintronics XII, 1109045 (16 September 2019); https://doi.org/10.1117/12.2528292
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neurons

Spintronics

Magnetism

Neural networks

CMOS technology

Back to Top