The human
brain efficiently executes highly sophisticated tasks, such as image and speech
recognition, with an exceptionally lower energy budget than today’s computers
can. The development of energy-efficient and tunable artificial neurons capable
of emulating brain-inspired processes has, therefore, been a major research
goal for decades.
Researchers
at the University of Gothenburg and Tohoku University jointly reported on an
important experimental advance in this direction, demonstrating a novel
voltage-controlled spintronic microwave oscillator capable of closely imitating
the non-linear oscillatory neural networks of the human brain.
The research team developed a voltage-controlled spintronic oscillator, whose properties can be strongly tuned, with negligible energy consumption. “This is an important breakthrough as these so-called spin Hall nano-oscillators (SHNOs) can act as interacting oscillator-based neurons but have so far lacked an energy-efficient tuning scheme — an essential prerequisite to train the neural networks for cognitive neuromorphic tasks,” proclaimed Shunsuke Fukami, co-author of the study. “The expansion of the developed technology can also drive the tuning of the synaptic interactions between each pair of spintronic neurons in a large complex oscillatory neural network.”
Scanning
electron microscopy image and schematic of cross-sectional structure of the
created spin-Hall nano-oscillator device with the gate electrode. Courtesy: Johan
Åkerman and Shunsuke Fukami.
Earlier
this year, the Johan Åkerman group at the University of Gothenburg
demonstrated, for the first time, 2D mutually synchronized arrays accommodating
100 SHNOs while occupying an area of less than a square micron. The network can
mimic neuron interactions in our brain and carry out cognitive tasks. However,
a major bottleneck in training such artificial neurons to produce different
responses to different inputs has been the lack of the scheme to control
individual oscillator inside such networks.
The Johan Åkerman group teamed up with Hideo Ohno and Shunsuke Fukami at Tohoku University to develop a bow tie-shaped spin Hall nano-oscillator made from an ultrathin W/CoFeB/MgO material stack with an added functionality of a voltage controlled gate over the oscillating region [Fig. 1]. Using an effect called voltage-controlled magnetic anisotropy (VCMA), the magnetic and magnetodynamic properties of CoFeB ferromagnet, consisting of a few atomic layers, can be directly controlled to modify the microwave frequency, amplitude, damping, and, thus, the threshold current of the SHNO [Fig. 2].
Experimental result of oscillation property under various gate voltages. Red and yellow regions mean a strong oscillation taking place. One can see that the oscillation property changes with the gate voltage. Courtesy: Johan Åkerman and Shunsuke Fukami
The
researchers also found a giant modulation of SHNO damping up to 42% using
voltages from -3 to +1 V in the bow-tied geometry. The demonstrated approach
is, therefore, capable of independently turning individual oscillators on/off
within a large synchronized oscillatory network driven by a single global drive
current. The findings are also valuable since they reveal a new mechanism of
energy relaxation in patterned magnetic nanostructures.
Fukami
notes that “With readily available energy-efficient independent control of the
dynamical state of individual spintronic neurons, we hope to efficiently train
large SHNO networks to carry out complex neuromorphic tasks and scale up
oscillator-based neuromorphic computing schemes to much larger network sizes.”
Collaboration
between Tohoku University and the University of Gothenburg will continue to
strengthen as Tohoku University has recently joined the Sweden-Japan
collaborative network MIRAI 2.0, a project that aims to enhance research
collaborations between Swedish and Japanese universities.