Multilayer spintronic neural networks with radiofrequency connections

Electrical Control of Magnetic Resonance in Phase Change Materials

Metal-insulator transitions (MITs) in resistive switching materials can be triggered by an electric stimulus that produces significant changes in the electrical response. When these phases have distinct magnetic characteristics, dramatic changes in the spin excitations are also expected. The transition metal oxide La0.7Sr0.3MnO3 (LSMO) is a ferromagnetic metal at low temperatures and a paramagnetic insulator above room temperature. When LSMO is in its metallic phase, a critical electrical bias has been shown to lead to an MIT that results in the formation of a paramagnetic resistive barrier transverse to the applied electric field. Using spin-transfer ferromagnetic resonance spectroscopy, we show that even for electrical biases less than the critical value that triggers the MIT, there is magnetic phase separation, with the spin-excitation resonances varying systematically with applied bias. Therefore, voltage-triggered MITs in LSMO can alter magnetic resonance characteristics, offering an effective method for tuning synaptic weights in neuromorphic circuits.

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach's efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

Antiferromagnetic artificial neuron modeling of the withdrawal reflex

Replicating neural responses observed in biological systems using artificial neural networks holds significant promise in the fields of medicine and engineering. In this study, we employ ultra-fast artificial neurons based on antiferromagnetic (AFM) spin Hall oscillators to emulate the biological withdrawal reflex responsible for self-preservation against noxious stimuli, such as pain or temperature. As a result of utilizing the dynamics of AFM neurons, we are able to construct an artificial neural network that can mimic the functionality and organization of the biological neural network responsible for this reflex. The unique features of AFM neurons, such as inhibition that stems from an effective AFM inertia, allow for the creation of biologically realistic neural network components, like the interneurons in the spinal cord and antagonist motor neurons. To showcase the effectiveness of AFM neuron modeling, we conduct simulations of various scenarios that define the withdrawal reflex, including responses to both weak and strong sensory stimuli, as well as voluntary suppression of the reflex.

Sparse reservoir computing with vertically coupled vortex spin-torque oscillators for time series prediction

Spin torque nano-oscillators possessing fast nonlinear dynamics and short-term memory functions are potentially able to achieve energy-efficient neuromorphic computing. In this study, we introduce an activation-state controllable spin neuron unit composed of vertically coupled vortex spin torque oscillators and aV-Isource circuit is proposed and used to build an energy-efficient sparse reservoir computing (RC) system to solve nonlinear dynamic system prediction task. Based on micromagnetic and electronic circuit simulation, the Mackey-Glass chaotic time series and the real motor vibration signal series can be predicted by the RC system with merely 20 and 100 spin neuron units, respectively. Further study shows that the proposed sparse reservoir system could reduce energy consumption without significantly compromising performance, and a minimal response from inactivated neurons is crucial for maintaining the system's performance. The accuracy and signal processing speed show the potential of the proposed sparse RC system for high-performance and low-energy neuromorphic computing.

Domain wall magnetic tunnel junction-based artificial synapses and neurons for all-spin neuromorphic hardware

We report a breakthrough in the hardware implementation of energy-efficient all-spin synapse and neuron devices for highly scalable integrated neuromorphic circuits. Our work demonstrates the successful execution of all-spin synapse and activation function generator using domain wall-magnetic tunnel junctions. By harnessing the synergistic effects of spin-orbit torque and interfacial Dzyaloshinskii-Moriya interaction in selectively etched spin-orbit coupling layers, we achieve a programmable multi-state synaptic device with high reliability. Our first-principles calculations confirm that the reduced atomic distance between 5d and 3d atoms enhances Dzyaloshinskii-Moriya interaction, leading to stable domain wall pinning. Our experimental results, supported by visualizing energy landscapes and theoretical simulations, validate the proposed mechanism. Furthermore, we demonstrate a spin-neuron with a sigmoidal activation function, enabling high operation frequency up to 20 MHz and low energy consumption of 508 fJ/operation. A neuron circuit design with a compact sigmoidal cell area and low power consumption is also presented, along with corroborated experimental implementation. Our findings highlight the great potential of domain wall-magnetic tunnel junctions in the development of all-spin neuromorphic computing hardware, offering exciting possibilities for energy-efficient and scalable neural network architectures.

Temperature effect on a weighted vortex spin-torque nano-oscillator for neuromorphic computing

In this work, we present fabricated magnetic tunnel junctions (MTJs) that can serve as magnetic memories (MMs) or vortex spin-torque nano-oscillators (STNOs) depending on the device geometry. We explore the heating effect on the devices to study how the performance of a neuromorphic computing system (NCS) consisting of MMs and STNOs can be enhanced by temperature. We further applied a neural network for waveform classification applications. The resistance of MMs represents the synaptic weights of the NCS, while temperature acts as an extra degree of freedom in changing the weights and TMR, as their anti-parallel resistance is temperature sensitive, and parallel resistance is temperature independent. Given the advantage of using heat for such a network, we envision using a vertical-cavity surface-emitting laser (VCSEL) to selectively heat MMs and/or STNO when needed. We found that when heating MMs only, STNO only, or both MMs and STNO, from 25 to 75 °C, the output power of the STNO increases by 24.7%, 72%, and 92.3%, respectively. Our study shows that temperature can be used to improve the output power of neural networks, and we intend to pave the way for future implementation of a low-area and high-speed VCSEL-assisted spintronic NCS.

Multistate Compound Magnetic Tunnel Junction Synapses for Digital Recognition

The quest to mimic the multistate synapses for bioinspired computing has triggered nascent research that leverages the well-established magnetic tunnel junction (MTJ) technology. Early works on the spin transfer torque MTJ-based artificial neural network (ANN) are susceptible to poor thermal reliability, high latency, and high critical current densities. Meanwhile, work on spin-orbit torque (SOT) MTJ-based ANN mainly utilized domain wall motion, which yields negligibly small readout signals differentiating consecutive states and has designs that are incompatible with technological scale-up. Here, we propose a multistate device concept built upon a compound MTJ consisting of multiple SOT-MTJs (number of MTJs, n = 1-4) on a shared write channel, mimicking the spin-based ANN. The n + 1 resistance states representing varying synaptic weights can be tuned by varying the voltage pulses (±1.5-1.8 V), pulse duration (100-300 ns), and applied in-plane fields (5.5-10.5 mT). A large TMR difference of more than 13.6% is observed between two consecutive states for the 4-cell compound MTJ, a 4-fold improvement from reported state-of-the-art spin-based synaptic devices. The ANN built upon the compound MTJ shows high learning accuracy for digital recognition tasks with incremental states and retraining, achieving test accuracy as high as 95.75% in the 4-cell compound MTJ. These results provide an industry-compatible platform to integrate these multistate SOT-MTJ synapses directly into neuromorphic architecture for in-memory and unconventional computing applications.

Non-hermiticity in spintronics: oscillation death in coupled spintronic nano-oscillators through emerging exceptional points

The emergence of exceptional points (EPs) in the parameter space of a non-hermitian (2D) eigenvalue problem has long been interest in mathematical physics, however, only in the last decade entered the scope of experiments. In coupled systems, EPs give rise to unique physical phenomena, and enable the development of highly sensitive sensors. Here, we demonstrate at room temperature the emergence of EPs in coupled spintronic nanoscale oscillators and exploit the system's non-hermiticity. We observe amplitude death of self-oscillations and other complex dynamics, and develop a linearized non-hermitian model of the coupled spintronic system, which describes the main experimental features. The room temperature operation, and CMOS compatibility of our spintronic nanoscale oscillators means that they are ready to be employed in a variety of applications, such as field, current or rotation sensors, radiofrequeny and wireless devices, and in dedicated neuromorphic computing hardware. Furthermore, their unique and versatile properties, notably their large nonlinear behavior, open up unprecedented perspectives in experiments as well as in theory on the physics of exceptional points expanding to strongly nonlinear systems.