Linear and symmetric conductance response of magnetic domain wall type spin-memristor for analog neuromorphic computing

Shibata, Tatsuo; Shinohara, Tetsuhito; Ashida, T.; Ohta, M.; Ito, Kuniyasu; Yamada, Satoshi; Terasaki, Yukio; Sasaki, T.

doi:10.35848/1882-0786/ab7e07

Cited by 30 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the probability of exposing the tunnel barrier is slightly larger. At present, the experimental realization of DW-MTJ devices is very limited and the existing literature reports TMR values of less than ∼50%. , In an optimized fabrication process, even if we lose 50% of the TMR at the device level, we can still achieve 8 distinguishable resistance states. For instance, if the low resistance state is at 1000 Ω.…”

Section: Resultsmentioning

confidence: 99%

Ultralow Energy Domain Wall Device for Spin-Based Neuromorphic Computing

et al. 2023

View full text Add to dashboard Cite

Neuromorphic computing (NC) is gaining wide acceptance as a potential technology to achieve lowpower intelligent devices. To realize NC, researchers investigate various types of synthetic neurons and synaptic devices, such as memristors and spintronic devices. In comparison, spintronics-based neurons and synapses have potentially higher endurance. However, for realizing low-power devices, domain wall (DW) devices that show DW motion at low energies�typically below pJ/bit�are favored. Here, we demonstrate DW motion at current densities as low as 10 6 A/m 2 by engineering the β-W spin−orbit coupling (SOC) material. With our design, we achieve ultralow pinning fields and current density reduction by a factor of 10 4 . The energy required to move the DW by a distance of about 18.6 μm is 0.4 fJ, which translates into the energy consumption of 27 aJ/bit for a bit-length of 1 μm. With a meander DW device configuration, we have established a controlled DW motion for synapse applications and have shown the direction to make ultralow energy spin-based neuromorphic elements.

show abstract

Section: Resultsmentioning

confidence: 99%

Ultralow Energy Domain Wall Device for Spin-Based Neuromorphic Computing

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Another design by Sasaki's group utilized a three‐terminal Co/Pd multilayer DW MTJ with inherent linear and symmetric conductance response upon applied pulses. [ 293 ] By using optical lithography and Ar ion milling, they managed to achieve an element with 200 steps, allowing a broad, linear dynamic range of conductance to be modulated over 200 pulses. Furthermore, spintronic memristors provide solutions for realizing interconnectivity between thousands of artificial synapses to a single neuron, mimicking the average biological synapse per neuron ratio.…”

Section: Discussionmentioning

confidence: 99%

Stimuli‐Responsive Memristive Materials for Artificial Synapses and Neuromorphic Computing

et al. 2021

View full text Add to dashboard Cite

Neuromorphic computing holds promise for building next‐generation intelligent systems in a more energy‐efficient way than the conventional von Neumann computing architecture. Memristive hardware, which mimics biological neurons and synapses, offers high‐speed operation and low power consumption, enabling energy‐ and area‐efficient, brain‐inspired computing. Here, recent advances in memristive materials and strategies that emulate synaptic functions for neuromorphic computing are highlighted. The working principles and characteristics of biological neurons and synapses, which can be mimicked by memristive devices, are presented. Besides device structures and operation with different external stimuli such as electric, magnetic, and optical fields, how memristive materials with a rich variety of underlying physical mechanisms can allow fast, reliable, and low‐power neuromorphic applications is also discussed. Finally, device requirements are examined and a perspective on challenges in developing memristive materials for device engineering and computing science is given.

show abstract

“…These devices offer low-power consumption, and highly stable and reproducible operation [15][16][17][18][19][20] , according to the experimentally well-established model 21,22 . Experimental demonstrations of DW-based neuromorphic components using magnetic tunnel junctions (MTJs) have been reported 23,24 . MTJ-based resistance output devices generate a current output from the voltage input signal.…”

Section: Introductionmentioning

confidence: 99%

Integrated neuromorphic computing networks by artificial spin synapses and spin neurons

et al. 2021

View full text Add to dashboard Cite

One long-standing goal in the emerging neuromorphic field is to create a reliable neural network hardware implementation that has low energy consumption, while providing massively parallel computation. Although diverse oxide-based devices have made significant progress as artificial synaptic and neuronal components, these devices still need further optimization regarding linearity, symmetry, and stability. Here, we present a proof-of-concept experiment for integrated neuromorphic computing networks by utilizing spintronics-based synapse (spin-S) and neuron (spin-N) devices, along with linear and symmetric weight responses for spin-S using a stripe domain and activation functions for spin-N. An integrated neural network of electrically connected spin-S and spin-N successfully proves the integration function for a simple pattern classification task. We simulate a spin-N network using the extracted device characteristics and demonstrate a high classification accuracy (over 93%) for the spin-S and spin-N optimization without the assistance of additional software or circuits required in previous reports. These experimental studies provide a new path toward establishing more compact and efficient neural network systems with optimized multifunctional spintronic devices.

show abstract

Linear and symmetric conductance response of magnetic domain wall type spin-memristor for analog neuromorphic computing

Cited by 30 publications

References 29 publications

Ultralow Energy Domain Wall Device for Spin-Based Neuromorphic Computing

Ultralow Energy Domain Wall Device for Spin-Based Neuromorphic Computing

Stimuli‐Responsive Memristive Materials for Artificial Synapses and Neuromorphic Computing

Integrated neuromorphic computing networks by artificial spin synapses and spin neurons

Contact Info

Product

Resources

About