A spintronic device to mimic artificial neuron for neuromorphic computing was developed by researchers in this study. This spintronic neuron device can produce stochastic spiking signal with an ultra-low power (< 1 nW) while the frequency of the spiking signal is controllable by magnetic field or voltage bias.
They applied this spintronic neuron device to construct an artificial neural network, and realized the recognition of the Mixed National Institute of Standards and Technology (MNIST) handwritten digits with a recognition rate reaching 95%.
This study enables to mimic neurons using spintronic devices with low energy consumption and multi-control methods, which advances the quest to create energy-efficient spintronic systems for brain-like cognitive computing.
ZENG Zhongming
Suzhou institute of Nano-Tech and Nano-Bionic
E-mail: zmzeng2012@sinano.ac.cn
A research group led by Prof. ZHUGE Fei at the Ningbo Institute of Materials Technology and Engineering developed an all-optically controlled (AOC) analog memristor whose memconductance can be reversibly tuned by varying only the wavelength of the controlling light.
86-10-68597521 (day)
86-10-68597289 (night)
52 Sanlihe Rd., Xicheng District,
Beijing, China (100864)
Copyright © 2002 - Chinese Academy of Sciences
