Memristor Array Research Articles

Van der Waals Engineering of One-Transistor-One-Ferroelectric-Memristor Architecture for an Energy-Efficient Neuromorphic Array.

Two-dimensional-material-based memristor arrays hold promise for data-centric applications such as artificial intelligence and big data. However, accessing individual memristor cells and effectively controlling sneak current paths remain challenging. Here, we propose a van der Waals engineering approach to create one-transistor-one-memristor (1T1M) cells by assembling the emerging two-dimensional ferroelectric CuCrP2S6 with MoS2 and h-BN. The memory cell exhibits high resistance tunability (106), low sneak current (120 fA), and low static power (12 fW). A neuromorphic array with greatly reduced crosstalk is experimentally demonstrated. The nonvolatile resistance switching is driven by electric-field-induced ferroelectric polarization reversal. This van der Waals engineering approach offers a universal solution for creating compact and energy-efficient 2D in-memory computation systems for next-generation artificial neural networks.

Efficient nonlinear function approximation in analog resistive crossbars for recurrent neural networks

Analog In-memory Computing (IMC) has demonstrated energy-efficient and low latency implementation of convolution and fully-connected layers in deep neural networks (DNN) by using physics for computing in parallel resistive memory arrays. However, recurrent neural networks (RNN) that are widely used for speech-recognition and natural language processing have tasted limited success with this approach. This can be attributed to the significant time and energy penalties incurred in implementing nonlinear activation functions that are abundant in such models. In this work, we experimentally demonstrate the implementation of a non-linear activation function integrated with a ramp analog-to-digital conversion (ADC) at the periphery of the memory to improve in-memory implementation of RNNs. Our approach uses an extra column of memristors to produce an appropriately pre-distorted ramp voltage such that the comparator output directly approximates the desired nonlinear function. We experimentally demonstrate programming different nonlinear functions using a memristive array and simulate its incorporation in RNNs to solve keyword spotting and language modelling tasks. Compared to other approaches, we demonstrate manifold increase in area-efficiency, energy-efficiency and throughput due to the in-memory, programmable ramp generator that removes digital processing overhead.

Research Progress of Neuromorphic Chips

The increasing amount of data in the era of artificial intelligence imposes higher demands on the computational power of neural networks, and in order to fulfill this demand, there is a pressing need to overcome the limitations imposed by the von Neumann architecture's memory wall. Memristors, with their characteristics, are considered the optimal electronic devices for implementing neuromorphic computing. Therefore, in order to better utilize memristors for the design and research of neuromorphic chips, this paper summarizes and comparatively analyzes the memristor characteristics, the RRAM basic principles, memristor array research, crossbar array designs based on memristors, and the study of memristor-based neuromorphic computing chips through the review. The paper emphasizes the challenges that memristor-based neuromorphic computing chips still face in the future, such as non-linear resistance variation. In addition, potential future research directions for amnesia-based neuromorphic computing chips, including amnesia architecture, programming techniques, and instruction set development, are discussed and investigated

Self-supervised video processing with self-calibration on an analogue computing platform based on a selector-less memristor array

Self-supervised video processing with self-calibration on an analogue computing platform based on a selector-less memristor array

Demonstration of a novel majority logic in a memristive crossbar array for in-memory parallel computing.

A memristive crossbar array can execute Boolean logic operations directly within the memory, which is highly noteworthy as it addresses the data bottleneck issue in traditional von Neumann computing. Although its potential has been widely demonstrated, achieving practical levels of operational reliability and computational efficiency remains a challenge. Here, we introduce a three-input majority logic gate supported by near-memory operations, serving as a universal gate and achieving both robust reliability and high efficiency in versatile logic operations. We fabricated a highly reliable HfOx-based memristive array, incorporating a series resistor to increase the reset voltage of the memristor, thereby increasing the operational voltage margin of the gate operation. This ensured reliable operation of the majority gate, resulting in successful experimental proof of combined 1-bit full adder and subtractor operations performed in 5 steps using 7 cells. Additionally, we propose that an N-bit parallel prefix adder (PPA) operation is possible in O(log2 N) steps, by taking advantage of the parallel operation capability of the majority gate. This achieves 8.5× higher spatiotemporal efficiency than the previously reported NOR-based logic system in 64-bit adder operation. Moreover, as N increases, the spatiotemporal efficiency further improves, which significantly enhances the applicability of memristive logic-in-memory.

Optoelectronic stimuli-driven switchable memristors with multilevel resistance states for neuromorphic vision sensors

The developed optoelectronic synaptic devices with resistive switching enable efficient, fault-resistant image recognition. The PMMA/ZnO/2IF memristor array advances neuromorphic vision systems, offering high accuracy and low power consumption.

All-Optically Controlled Memristive Device Based on Cu2O/TiO2 Heterostructure Toward Neuromorphic Visual System.

The optoelectronic memristor integrates the multifunctionalities of image sensing, storage, and processing, which has been considered as the leading candidate to construct novel neuromorphic visual system. In particular, memristive materials with all-optical modulation and complementary metal oxide semiconductor (CMOS) compatibility are highly desired for energy-efficient image perception. As a p-type oxide material, Cu2O exhibits outstanding theoretical photoelectric conversion efficiency and broadband photoresponse. In this work, an all-optically controlled memristor based on the Cu2O/TiO2/sodium alginate nanocomposite film is developed. Optical potentiation and depression behaviors have been implemented by utilizing visible (680 nm) and ultraviolet (350 nm) light. Furthermore, a 7 × 9 optoelectronic memristive array with satisfactory device variation and environment stability is constructed to emulate the image preprocessing function in biological retina. The random noise can be reduced effectively by utilizing bidirectional optical input. Beneficial from the image preprocessing function, the accuracy of handwritten digit classification increases more than 60%. Our work presents a pathway toward high-efficient neuromorphic visual system and promotes the development of artificial intelligence technology.

Fully Resistive In‐Memory Cryptographic Engine with Dual‐Polarity Memristive Crossbar Array

AbstractAs data volume and complexity increase, conventional software‐based encryption methods face significant challenges, including vulnerability to attacks and high computational demands. This study proposes a hardware‐based cryptographic engine using a dual‐polarity memristive crossbar array with Ta/HfO2/RuO2 memristors, utilizing stochastic and deterministic operations for enhanced security and efficiency. The system integrates random key generation and XOR‐based logic operations within the memristive array, enabling robust encryption and decryption of binary data with a fully resistive data representation. Experimental validation of alphabet image data encryption and the array scale simulation of individual fingerprint authentication are conducted to validate the robustness of the proposed hardware and cryptographic method. The results demonstrate the potential of the proposed hardware for homomorphic encryption, enabling secure data processing without decryption, which can pave the way for memristive hardware to evolve into resistance‐based digital computing hardware.

The Model and Simulation of Memristor

Memristor is an emerging electronic component, tremendous efforts have been made in the fields of memristor, motivated by its unique resistor switching feature, as well as the good compatibility with the current integrated circuit (IC) technologies. It has been widely accepted that memristor would be a powerful candidate for constructing the brain-like computing hardware system in the next generation of electronics. Even so, there are still challenges in the development of the memristor IC and the calculation system based on it. For an example, the lack of memristor simulation module hinders its automatic design. Herein, we would like to propose a method for simulating the feature of the memristor. Firstly, based on the conductive filament based physical principle of memristor, calculations are conducted to simulate the basic electronic features of memristor. The good fitness confirms the feasibility of the proposed method. Second, the memristor’s resistance switching feature is modelled by Spice, a popular design platform. With the use of Voltage-Controlled Current Source (VCCS) in Spice, a modulus of memristor is established and executed to simulate the switched resistances under different bias voltages. In summary, this work demonstrates the feasibility of the proposed simulating method, it may provide an easy-to-operate way to improve design efficiency of active memristor arrays

Room‐Temperature‐Integrated Flexible Diffusive Oxide Memristors for Artificial Nociceptive Systems

AbstractNovel areas of human–computer interaction and intelligent robotics are rapidly boosted by flexible electronic devices, among which artificial nociceptors for pain perception are considered essential sensory devices. Recently, flexible diffusive memristors with volatile behavior are extensively studied to emulate biological synapses and neurons because of their rich threshold–switching dynamics, which are crucial for nociceptive functions. Herein, flexible diffusive memristors with an Ag/TaO1.8/TaO2.7/TaO1.8/Ag (ATTTA) structure are fabricated at room temperature, demonstrating a high switching ratio of 107, an ultra‐fast turn‐on speed of 40 ns, a long endurance up to 104 sweep cycles, low positive and negative threshold variation rates (6.7%/7.8%) for 50 devices, a good thermal stability at an 85 °C measurement temperature, and a high flexibility under an 8 mm bending radius. These high performances are attributed to the oxygen‐rich TaO2.7 layer, which can prevent the excessive migration of Ag atoms. Moreover, multiple biological nociceptor functions, including threshold firing, no adaptation, and sensitization, are successfully emulated in the flexible ATTTA diffusive memristor. Accordingly, the human–skin nociceptive system is successfully emulated by integrating ATTTA diffusive memristor array with force–sensing resistors (FSRs), which enables stereoscopic injury perception of inhomogeneous stimuli.

Self‐Rectifying Switching Memory Based on HfOx/FeOx Semiconductor Heterostructure for Neuromorphic Computing

AbstractSneak‐path current is one of the biggest barriers for large‐scale passive memristor array integration. An ideal self‐rectifying resistance random access memory (SR‐RRAM) is a desirable solution but it has not been demonstrated today for optimizing comprehensive indexes for neuromorphic computing. The HfOx/FeOx semiconductor heterojunction SR‐RRAM with a robust self‐rectifying switching behavior featured by an average rectifying ratio (≈104), high resistance ratio (>106), high cycling endurance (>104 cycles), high computing precision (>6 bits) and synaptic plasticity such as paired‐pulse facilitation (PPF) and the spike‐timing‐dependent plasticity (STDP) for artificial intelligence recognition is developed using the unidirectional conductivity feature of p‐n junction. The electron hopping, tunneling, and blocking in this semiconductor heterojunction that is verified by the energy band mode based on UV photoelectron spectroscopy (UPS) technology and low‐energy inverse photoelectron spectroscopy (LEIPS) and in situ high resolution transmission electron microscopy (HR‐TEM) observation plays a dominant role in the self‐rectifying analog switching behaviors. This work provides energy‐band engineering for the large‐scale memristor array integration, representing a significant advancement in hardware for neuromorphic computing.

Design and Application of Programmable Analog Computing Circuit for Kalman Filter Algorithm Based on Memristive Array

Design and Application of Programmable Analog Computing Circuit for Kalman Filter Algorithm Based on Memristive Array

Memristor Array Based on Wafer-Scale 2D HfS2 for Dual-Mode Physically Unclonable Functions.

Conventional Si-based physically unclonable functions (PUFs) take advantage of the unique variations in the fabrication processes. However, these PUFs are hindered by limited entropy sources and susceptibility to noise interference. Here we present a memristive device based on wafer-scale (2-in.) two-dimensional (2D) hafnium disulfide (HfS2) grown by molecular beam epitaxy (MBE). The polycrystalline HfS2 thin film can offer enhanced entropy sources for PUF applications, such as lattice defects, which can facilitate the random formation of conductive filaments and result in significant device-to-device (D2D) variations. Our proposed PUF design seamlessly integrates two distinct operating modes within a single circuit module. First, a reconfigurable and highly secure mode 1, and second, an ultrareliable mode 2, both with near-ideal Entropy (∼1.0), normalized Hamming distance (∼0.5) and correlation coefficient (∼0.0). Additionally, a predictive Fourier regression model further confirms the unpredictable nature of our dual-mode PUF, with an average prediction accuracy of ∼50%.

A High-Stability Pressure-Sensitive Implantable Memristor for Pulmonary Hypertension Monitoring.

Pulmonary hypertension (PH) significantly affects the quality of life and lifespan of humans and has promoted the development of flexible implantable electronic devices for PH diagnosis and prevention. Traditional implantable devices based on the von Neumann architecture face insurmountable challenges in processing large amounts of biological data due to computational bottlenecks. Memristors, with integrated in-memory sensing and computing capabilities, can effectively eliminate computational bottlenecks and become one of the most promising products in implantable devices for health monitoring. Here, a memristor with the Ag/MnO2/BaTiO3/FTO structure is implemented and implanted into Sprague‒Dawley (SD) rats. With polydimethylsiloxane (PDMS) packaging, the device can be continuously worked in vivo for up to four weeks, demonstrating excellent stability and biocompatibility. Furthermore, a memristive sensor array is designed for pulmonary artery blood pressure monitoring based on the pressure-responsive characteristics of the as-prepared memristive device. The front-end memristive sensor array can collect and feedback pressure signal, while noise reduction is achieved through memristive logic circuits, and ultimately the memristor neural network processes and classifies the information. Therefore, this work demonstrates the potential of implantable memristors for pulmonary artery pressure monitoring and provides new inspiration for the design of efficient, real-time, and reliable implantable pressure monitoring devices in medical health monitoring.

Practical hardware demonstration of a multi-sensor goal-oriented semantic signal processing and communications network

Recent advancements in machine learning, particularly real-time extraction of rich semantic information, reshape signal processing techniques and related hardware architectures. To address the highly challenging requirements of next-generation signal processing applications in networked platforms, we investigate low-power hardware implementation alternatives for a multi-sensor, goal-oriented semantic communications network. Specifically, we focus on cost-effective Raspberry Pis in a multi-sensor semantic video communication application, showcasing adaptability from traditional CPU/GPU configurations. Additionally, we provide a preliminary investigation on implementing semantic extraction tasks through in-memory computation using memristor arrays to further emphasize the potential future of low-power low-cost semantic signal processing. Hardware demonstrations using Raspberry Pi 4Bs and simulations with in-memory computation architectures offer promising hardware architectures with cost-effective and low-power sensor alternatives to the next-generation semantic signal processing applications and semantic communication systems.

An Antagonistic Photovoltaic Memristor for Bioinspired Active Contrast Adaptation.

Machine vision systems that consist of cameras and image-processing components for visual inspection and identification tasks play a critical role in various intelligent applications, including pilotless vehicles and surveillance systems. However, current systems usually possess a limited dynamic range and fixed photoresponsivity, restricting their capability of gaining high-fidelity images when encoding a high-contrast scene. Here, it is shown that a photovoltaic memristor incorporating two antagonistic photovoltaic junctions can autonomously adjust its response to varying light stimuli, enabling the amplification of shadows and inhibition of highlight saturation. Due to the dynamic photodoping effect at the p-n junction with an asymmetrical profile, the photocurrent polarities of the antagonistic memristor can be changed as the light intensity increases. The light-intensity-dependent switchable photovoltaic behaviors match Weber's law where photosensitivity is inversely proportional to the light stimuli. An 11×11 memristor array is used to detect a high-contrast scene with light intensities ranging from 1 to 5×104 µW cm-2, achieving a similar active contrast adaptation performance compared with the human visual systems (less than 1.2 s at 94 dB). This work paves the way for innovative neuromorphic device designs and may lead to the development of state-of-the-art active visual adaptation photosensors.

Mott Memristors for Neuromorphics

AbstractNeuromorphic computing has emerged as a key solution for overcoming the challenge of von Neumann bottleneck, offering a pathway to more efficient and biologically inspired computing systems. A crucial advancement in this field is the utilization of Mott insulators, where the metal‐insulator transition (MIT) elicits substantial alterations in material properties, infusing renewed vigor into the progression of neuromorphic systems. This review begins by explaining the MIT mechanisms and the preparation processes of Mott insulators, followed by an introduction of Mott memristors and memristor arrays, showing different types of multidimensional integration styles. The applications of Mott memristor in neuromorphic computing are then discussed, which include artificial synapse designs and various artificial neuron architectures for sensory recognition and logic calculation. Finally, facing challenges and potential future directions are outlined for utilizing Mott memristors in the advancement of neuromorphic computing. This review aims to provide a thorough understanding of the latest advancements in Mott memristors and their applications, offering a comprehensive reference for further research in related areas, and contributing to bridging the gap between traditional silicon‐based electronics and future brain‐inspired architectures.

Site-Selective Nanowire Synthesis and Fabrication of Printed Memristor Arrays with Ultralow Switching Voltages on Flexible Substrate.

Large area electronics (LAE) with the capability to sense and retain information are crucial for advances in applications such as wearables, digital healthcare, and robotics. The big data generated by these sensor-laden systems need to be scaled down or processed locally. In this regard, brain-inspired computing and in-memory computing have attracted considerable interest. However, suitable architectures have mainly been developed using costly and resource-intensive conventional lithography-based methods. There is a need for the development of innovative, resource-efficient fabrication routes that enable such devices and concepts. Herein, we present ZnO nanowire (NW)-based memristors on a polyimide substrate fabricated by a LAE-compatible and resource-efficient route comprising solution processing and printing technologies. High-resolution "drop-on-demand" and "direct ink write" printers are employed to deposit metallic layers (silver and gold) and a ZnO seed layer, needed for the site-selective growth of ZnO NWs via a low-cost hydrothermal method. The printed memristors show high bipolar resistance switching (ON/OFF ratio >103) between two nonvolatile states and consistent switching at ultralow voltages (all devices showed switching at amplitudes <200 mV), with the best performing device showing consistent cycled resistance switching over 4 orders of magnitude with SET and RESET voltages of about 71 and -57 mV, respectively. Thus, the presented devices offer reliable high resistance switching at the lowest reported voltage for printed memristors and prove to be competitive with many conventional nanofabrication-based devices. The presented results show the potential printed memristors technology holds for large-area, low-voltage sensing applications such as electronic skin.

Linearly programmable two-dimensional halide perovskite memristor arrays for neuromorphic computing.

The exotic properties of three-dimensional halide perovskites, such as mixed ionic-electronic conductivity and feasible ion migration, have enabled them to challenge traditional memristive materials. However, the poor moisture stability and difficulty in controlling ion transport due to their polycrystalline nature have hindered their use as a neuromorphic hardware. Recently, two-dimensional (2D) halide perovskites have emerged as promising artificial synapses owing to their phase versatility, microstructural anisotropy in electrical and optoelectronic properties, and excellent moisture resistance. However, their asymmetrical and nonlinear conductance changes still limit the efficiency of training and accuracy of inference. Here we achieve highly linear and symmetrical conductance changes in Dion-Jacobson 2D perovskites. We further build a 7 × 7 crossbar array based on analogue perovskite synapses, achieving a high device yield, low variation with synaptic weight storing capability, multi-level analogue states with long retention, and moisture stability over 7 months. We explore the potential of such devices in large-scale image inference via simulations and show an accuracy within 0.08% of the theoretical limit. The excellent device performance is attributed to the elimination of gaps between inorganic layers, allowing the halide vacancies to migrate homogeneously regardless of grain boundaries. This was confirmed by first-principles calculations and experimental analysis.

From Solid to Fluid: Novel Approaches in Neuromorphic Engineering.

Neuromorphic engineering is rapidly developing as an approach to mimicking processes in brains using artificial memristors, devices that change conductivity in response to the electrical field (resistive switching effect). Memristor-based neuromorphic systems can overcome the existing problems of slow and energy-inefficient computing that conventional processors face. In the Introduction, the basic principles of memristor operation and its applications are given. The history of switching in sandwich structures and granular metals is reviewed in the Historical Overview. Particular attention is paid to the fundamental articles from the pre-memristor era (the 1960s-70s), which demonstrated the first evidence of resistive switching and predicted the filamentary mechanism of switching. Multi-dimensionality in neuromorphic systems: Despite the powerful computational abilities of traditional memristor arrays, they cannot repeat many organizational characteristics of biological neural networks, i.e., their multi-dimensionality. This part reviews the unconventional nanowire- and nanoparticle-based neuromorphic systems that demonstrate incredible potential for use in reservoir computing due to the unique spiking change in conductance similar to firing in neurons. Liquid-based neuromorphic devices: The transition of neuromorphic systems from solid to liquid state broadens the possibilities for mimicking biological processes. In this section, ionic current memristors are reviewed and, the working principles of which bring us closer to the mechanisms of information transmittance in real synapses. Nanofluids: A novel direction in neuromorphic engineering linked to the application of nanofluids for the formation of reconfigurable nanoparticle networks with memristive properties is given in this section. The Conclusion t summarizes the bullet points of the Review and provides an outlook on the future of liquid-state neuromorphic systems.