Search

Osteoporosis is a metabolic bone disease characterized by a disruption in the balance between bone resorption and formation. Here, the authors identified high levels of lipid raft-related stomatin in osteoporosis patients and ovariectomized mice and demonstrate a mechanism by which it drives bone resorption.

A memristor-based architecture for federated learning can implement compute-in-memory technology for encryption and decryption computations, a physical unclonable function for key generation and a true random number generator for error polynomial generation all within the same memristor array and peripheral circuits.

Skyrmions, a type of topological spin texture, have garnered interest for use in spintronic devices. Typically, these devices necessitate moving the skyrmions via applied currents. Here, Yang et al demonstrate the driving of skyrmions by surface acoustic waves.

The practicality of memristor-based computation-in-memory (CIM) is limited by the specific hardware design and the manual parameters tuning process. Here, the authors develop a full-stack CIM system with both hardware and software design for improved flexibility and efficiency.

An analogue–digital unified compute-in-memory architecture can offer native support for floating-point-based complex regression tasks, providing improved accuracy and energy efficiency compared with pure analogue compute-in-memory systems.

A neuromorphic decoder for brain–computer interfaces that is based on a 128k-cell memristor chip can offer software-equivalent decoding performance and can adapt to changing brain signals.

The proposed edge detection based on ferroelectric field effect transistor does not rely on conventional convolution operation, realizing no-accuracy-loss, low-power (~10 fJ/per operation) and analogue-to-digital converter (ADC)-free edge computing.

This study introduces an in-memory deep Bayesian active learning framework that uses the stochastic properties of memristors for in situ probabilistic computations. This framework can greatly improve the efficiency and speed of artificial intelligence learning tasks, as demonstrated with a robot skill-learning task.

The authors demonstrate voltage-controlled multiferroic magnon torque in BiFeO₃ heterostructures, enabling reconfigurable logic-in-memory devices. This work highlights potential for low-power, scalable magnonics in room-temperature computing.

This study reports a fully integrated 128 × 8 optoelectronic memristor array with Si complementary metal–oxide–semiconductor circuits, featuring configurable multi-mode functionality. It demonstrates diversified in-sensor computing tasks and consumes 20 times less energy than GPUs.

Bacterial cells utilize cholesterol-enhanced pore formation to specifically target eukaryotic cells. Here, the authors present a class of bio-inspired, cholesterol-enhanced nanopores which display anticancer activities in vitro.

A magnetic spin Hall effect is reported in the collinear antiferromagnet Mn₂Au.

Metal gate electrodes with a high cohesive energy—platinum and tungsten—can be used to mitigate leakage currents and premature dielectric breakdown across chemical vapour deposition-grown multilayer hexagonal boron nitride, allowing the material to be used as a gate dielectric in two-dimensional-materials-based transistors.

The explosive growth of artificial intelligence calls for rapidly increasing computing power. Two reported photonic processors could meet these power requirements and revolutionize artificial-intelligence hardware.

Sound localization is one of the many learning tasks accomplished by the brain based on the binaural signals of the ears. Here, Wu et al demonstrate in-situ learning of sound localization function using a memristor array, with dramatic improvements in energy efficiency.

The rare lung cancer subtype pulmonary lymphoepithelioma-like carcinoma is linked to Epstein-Barr virus infection. Here, the authors provide a mutational landscape for this cancer, showing a low burden of somatic mutations and high prevalence of copy number variations.

The cycling disordering–ordering transition of low-misfit superlattice nanoprecipitates in metallic materials continuously annihilates radiation defects via a short-range atom-reshuffling process, giving rise to high radiation tolerance.

The ‘Tianjic’ hybrid electronic chip combines neuroscience-oriented and computer-science-oriented approaches to artificial general intelligence, demonstrated by controlling an unmanned bicycle.

A memristor-based artificial dendrite enables the neural network to perform high-accuracy computation tasks with reduced power consumption.

Linear diffractive structures are by themselves passive systems but researchers here exploit the non-linearity of a photodetector to realize a reconfigurable diffractive ‘processing’ unit. High-speed image and video recognition is demonstrated.

By integrating split ferroelectric capacitors with complementary characteristics in the same memory cell, this architecture tackles the problem of conflicting memory requirements for training and inference, which has long plagued edge intelligence applications.

Time-resolved magneto-optical Kerr microscopy, combined with micromagnetic simulations, can be used to detect spin–orbit torque switching of the magnetization and exchange bias in platinum/cobalt/iridium–manganese heterostructures on sub-nanosecond timescales.

Leaky integrate-and-fire artificial neurons based on diffusive memristors enable unsupervised weight updates of drift-memristor synapses in an integrated convolutional neural network capable of pattern recognition.

Though memristors can potentially emulate neuron and synapse functionality, useful signal energy is lost to Joule heating. Here, the authors demonstrate neuro-transistors with a pseudo-memcapacitive gate that actively process signals via energy-efficient capacitively-coupled neural networks.

Designing efficient 3D artificial neural networks chip remains a challenge. Here, the authors report a M3D-LIME chip with monolithic three-dimensional integration of hybrid memory architecture based on resistive random-access memory, which achieves a high classification accuracy of 96% in one-shot learning task while exhibiting 18.3× higher energy efficiency than GPU.

Memristive devices can provide energy-efficient neural network implementations, but they must be tailored to suit different network architectures. Wang et al. develop a trainable weight-sharing mechanism for memristor-based CNNs and ConvLSTMs, achieving a 75% reduction in weights without compromising accuracy.

A compute-in-memory neural-network inference accelerator based on resistive random-access memory simultaneously improves energy efficiency, flexibility and accuracy compared with existing hardware by co-optimizing across all hierarchies of the design.

The stochastic features of memristors make them suitable for computation and probabilistic sampling; however, implementing these properties in hardware is extremely challenging. Lin et al. introduce an approach that leverages the cycle-to-cycle read variability of memristors as a physical random variable for in situ, real-time random number generation, and demonstrate it on a risk-sensitive reinforcement learning task.

Image reconstruction algorithms raise critical challenges in massive data processing for medical diagnosis. Here, the authors propose a solution to significantly accelerate medical image reconstruction on memristor arrays, showing 79× faster speed and 153× higher energy efficiency than state-of-the-art graphics processing unit.

High-integration-density 2D–CMOS hybrid microchips for memristive applications are made demonstrating in-memory computation and electrical response suitable for the implementation of spiking neural networks representing an advance towards integration of 2D materials in microelectronic products and memristive applications.

Dynamic and non-volatile memristors can be used to create hardware-based reservoir and readout layers in artificial neural networks, providing a fully analogue signal processing chain for efficient data classification.

Using chips that mimic the human brain to perform cognitive tasks, namely neuromorphic computing, calls for low power and high efficiency hardware. Here, Yaoet al. show on-chip analogue weight storage by integrating non-volatile resistive memory into a CMOS platform and test it in facial recognition.

By using optoelectronic device arrays for chip-to-chip communication and neuromorphic cores based on memristor crossbar arrays for highly parallel data processing, reconfigurable and stackable hetero-integrated chips can be created for use in edge computing applications.

Reservoir computing has demonstrated high-level performance, however efficient hardware implementations demand an architecture with minimum system complexity. The authors propose a rotating neuron-based architecture for physically implementing all-analog resource efficient reservoir computing system.

Designing energy efficient and high performance brain-machine interfaces with millions of recording electrodes for in-situ analysis remains a challenge. Here, the authors develop a memristor-based neural signal analysis system capable of filtering and identifying epilepsy-related brain activities with an accuracy of 93.46%.

Here, the authors demonstrate an atomic threshold-switching field-effect transistor constructed by integrating a metal filamentary switch with a two-dimensional MoS₂ channel, and obtain abrupt steepness in the turn-on characteristics and 4.5 mV/dec subthreshold swing over five decades.

Designing efficient neuromorphic systems for complex temporal tasks remains a challenge. Zhong et al. develop a parallel memristor-based reservoir computing system capable of tuning critical parameters, achieving classification accuracy of 99.6% in spoken-digit recognition and time-series prediction error of 0.046 in the Hénon map.

The development of humanoid robots with artificial intelligence calls for smart solutions for tactile sensing systems that respond to dynamic changes in the environment. Here, Yoon et al. emulate non-adaption and sensitization function of a nociceptor—a sensory neuron—using diffusive oxide-based memristors.

A fully hardware-based memristor convolutional neural network using a hybrid training method achieves an energy efficiency more than two orders of magnitude greater than that of graphics-processing units.

Memristor devices have shown notable superiority in the realm of neuromorphic computing chips, particularly in artificial intelligence (AI) inference tasks. Researchers are now grappling with the intricacies of incorporating in situ learning capabilities into memristor-based chips, paving the way for more powerful edge intelligence.

Analogue computing based on memristors could offer a faster and more energy-efficient alternative to conventional digital computing in IoT applications.

Nanoscale magnetic skyrmions that are generated in metallic multilayers using on-chip heating diffuse from hot to cold regions and can be thermoelectrically detected via the Nernst voltage.

This Review examines the development of electrical reservoir computing, considering the architectures, physical nodes, and input and output layers of the approach, as well as performance benchmarks and the competitiveness of different implementations.