Improving linearity by introducing Al in HfO2 as a memristor synapse device

Investigation of the Versatile Utilization of Three-Dimensional Vertical Resistive Random-Access Memory in Neuromorphic Computing

The continuous advancement of computing technologies such as the Internet of Things and artificial intelligence emphasizes the need for innovative approaches to data processing. Faced with limitations in processing speed due to the exponentially increasing volume of data, conventional von-Neumann computing systems are transforming into a new paradigm called neuromorphic computing, inspired by the efficiency of the human brain. We fabricate three-dimensional vertical resistive random-access memory (VRRAM), which is highly suited for neuromorphic computing, and demonstrate its value as an artificial synapse. Beyond simulating simple synaptic functionalities such as spike-rate-dependent plasticity, spike-timing-dependent plasticity, and paired-pulse facilitation, we propose specific applications and experimentally implement them. In pattern recognition simulations based on the weight update characteristics of the fabricated VRRAM, the accuracy achieved in pattern recognition using appropriate pulse schemes reaches 90.4%. Additionally, we demonstrate adaptive learning behavior on the device by mimicking Pavlov's dog experiment with combinations of applied voltage pulses. Finally, we employ suitable write/erase pulse trains to implement binary representations for decimal numbers ranging from 0 to 15, thereby illustrating the significant potential of local devices for edge computing applications.

High-Linearity Ta2O5 Memristor and Its Application in Gaussian Convolution Image Denoising

In the image Gaussian filtering process, convolving with a Gaussian matrix is essential due to the numerous arithmetic computations involved, predominantly multiplications and additions. This can heavily tax the system's memory, particularly with frequent use. To address this issue, a W/Ta2O5/Ag memristor was employed to substantially mitigate the computational overhead associated with convolution operations. Additionally, an interlayer of ZnO was subsequently introduced into the memristor. The resulting Ta2O5/ZnO heterostructure layer exhibited improved linearity in the pulse response, which enhanced linearity facilitates easy adjustment of the conductance magnitude through a linear mapping of the number of pulses and the conductance. Subsequently, the conductance of the W/Ta2O5/ZnO/Ag bilayer memristor was employed as the weights for the convolution kernel in convolution operations. Gaussian noise removal in image processing was achieved by assembling a 5 × 5 memristor array as the kernel. When denoising was performed using memristor arrays, compared to denoising achieved through Gaussian matrix convolution, an average loss of less than 5% was observed. The provided memristors demonstrate significant potential in convolutional computations, particularly for subsequent applications in convolutional neural networks (CNNs).

Dynamic Effects Analysis in Fractional Memristor-Based Rulkov Neuron Model

Mathematical models such as Fitzhugh-Nagoma and Hodgkin-Huxley models have been used to understand complex nervous systems. Still, due to their complexity, these models have made it challenging to analyze neural function. The discrete Rulkov model allows the analysis of neural function to facilitate the investigation of neuronal dynamics or others. This paper introduces a fractional memristor Rulkov neuron model and analyzes its dynamic effects, investigating how to improve neuron models by combining discrete memristors and fractional derivatives. These improvements include the more accurate generation of heritable properties compared to full-order models, the treatment of dynamic firing activity at multiple time scales for a single neuron, and the better performance of firing frequency responses in fractional designs compared to integer models. Initially, we combined a Rulkov neuron model with a memristor and evaluated all system parameters using bifurcation diagrams and the 0-1 chaos test. Subsequently, we applied a discrete fractional-order approach to the Rulkov memristor map. We investigated the impact of all parameters and the fractional order on the model and observed that the system exhibited various behaviors, including tonic firing, periodic firing, and chaotic firing. We also found that the more I tend towards the correct order, the more chaotic modes in the range of parameters. Following this, we coupled the proposed model with a similar one and assessed how the fractional order influences synchronization. Our results demonstrated that the fractional order significantly improves synchronization. The results of this research emphasize that the combination of memristor and discrete neurons provides an effective tool for modeling and estimating biophysical effects in neurons and artificial neural networks.

HfAlOx-based ferroelectric memristor for nociceptor and synapse functions

Efficient data processing is heavily reliant on prioritizing specific stimuli and categorizing incoming information. Within human biological systems, dorsal root ganglions (particularly nociceptors situated in the skin) perform a pivotal role in detecting external stimuli. These neurons send warnings to our brain, priming it to anticipate potential harm and prevent injury. In this study, we explore the potential of using a ferroelectric memristor device structured as a metal-ferroelectric-insulator-semiconductor as an artificial nociceptor. The aim of this device is to electrically receive external damage and interpret signals of danger. The TiN/HfAlOx (HAO)/HfSiOx (HSO)/n+ Si configuration of this device replicates the key functions of a biological nociceptor. The emulation includes crucial aspects, such as threshold reactivity, relaxation, no adaptation, and sensitization phenomena known as "allodynia" and "hyperalgesia." Moreover, we propose establishing a connection between nociceptors and synapses by training the Hebbian learning rule. This involves exposing the device to injurious stimuli and using this experience to enhance its responsiveness, replicating synaptic plasticity.

Advances on MXene-Based Memristors for Neuromorphic Computing: A Review on Synthesis, Mechanisms, and Future Directions

Neuromorphic computing seeks to replicate the capabilities of parallel processing, progressive learning, and inference while retaining low power consumption by drawing inspiration from the human brain. By further overcoming the constraints imposed by the traditional von Neumann architecture, this innovative approach has the potential to revolutionize modern computing systems. Memristors have emerged as a solution to implement neuromorphic computing in hardware, with research based on developing functional materials for resistive switching performance enhancement. Recently, two-dimensional MXenes, a family of transition metal carbides, nitrides, and carbonitrides, have begun to be integrated into these devices to achieve synaptic emulation. MXene-based memristors have already demonstrated diverse neuromorphic characteristics while enhancing the stability and reducing power consumption. The possibility of changing the physicochemical properties through modifications of the surface terminations, bandgap, interlayer spacing, and oxidation for each existing MXene makes them very promising. Here, recent advancements in MXene synthesis, device fabrication, and characterization of MXene-based neuromorphic artificial synapses are discussed. Then, we focus on understanding the resistive switching mechanisms and how they connect with theoretical and experimental data, along with the innovations made during the fabrication process. Additionally, we provide an in-depth review of the neuromorphic performance, making a connection with the resistive switching mechanism, along with a compendium of each relevant performance factor for nonvolatile and volatile applications. Finally, we state the remaining challenges in MXene-based devices for artificial synapses and the next steps that could be taken for future development.

Exploring the Reconfigurable Memory Effect in Electroforming-Free YMnO3-Based Resistive Switches: Towards a Tunable Frequency Response

Memristors, since their inception, have demonstrated remarkable characteristics, notably the exceptional reconfigurability of their memory. This study delves into electroforming-free YMnO3 (YMO)-based resistive switches, emphasizing the reconfigurable memory effect in multiferroic YMO thin films with metallically conducting electrodes and their pivotal role in achieving adaptable frequency responses in impedance circuits consisting of reconfigurable YMO-based resistive switches and no reconfigurable passive elements, e.g., inductors and capacitors. The multiferroic YMO possesses a network of charged domain walls which can be reconfigured by a time-dependent voltage applied between the metallically conducting electrodes. Through experimental demonstrations, this study scrutinizes the impedance response not only for individual switch devices but also for impedance circuitry based on YMO resistive switches in both low- and high-resistance states, interfacing with capacitors and inductors in parallel and series configurations. Scrutinized Nyquist plots visually capture the intricate dynamics of impedance circuitry, revealing the potential of electroforming-free YMO resistive switches in finely tuning frequency responses within impedance circuits. This adaptability, rooted in the unique properties of YMO, signifies a paradigm shift heralding the advent of advanced and flexible electronic technologies.

Hardware implementation of memristor-based artificial neural networks

Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units operating in parallel. The low communication bandwidth between memory and processing units in conventional von Neumann machines does not support the requirements of emerging applications that rely extensively on large sets of data. More recent computing paradigms, such as high parallelization and near-memory computing, help alleviate the data communication bottleneck to some extent, but paradigm- shifting concepts are required. Memristors, a novel beyond-complementary metal-oxide-semiconductor (CMOS) technology, are a promising choice for memory devices due to their unique intrinsic device-level properties, enabling both storing and computing with a small, massively-parallel footprint at low power. Theoretically, this directly translates to a major boost in energy efficiency and computational throughput, but various practical challenges remain. In this work we review the latest efforts for achieving hardware-based memristive artificial neural networks (ANNs), describing with detail the working principia of each block and the different design alternatives with their own advantages and disadvantages, as well as the tools required for accurate estimation of performance metrics. Ultimately, we aim to provide a comprehensive protocol of the materials and methods involved in memristive neural networks to those aiming to start working in this field and the experts looking for a holistic approach.

Artificial sensory system based on memristive devices

In the biological nervous system, the integration and cooperation of parallel system of receptors, neurons, and synapses allow efficient detection and processing of intricate and disordered external information. Such systems acquire and process environmental data in real-time, efficiently handling complex tasks with minimal energy consumption. Memristors can mimic typical biological receptors, neurons, and synapses by implementing key features of neuronal signal-processing functions such as selective adaption in receptors, leaky integrate-and-fire in neurons, and synaptic plasticity in synapses. External stimuli are sensitively detected and filtered by "artificial receptors," encoded into spike signals via "artificial neurons," and integrated and stored through "artificial synapses." The high operational speed, low power consumption, and superior scalability of memristive devices make their integration with high-performance sensors a promising approach for creating integrated artificial sensory systems. These integrated systems can extract useful data from a large volume of raw data, facilitating real-time detection and processing of environmental information. This review explores the recent advances in memristor-based artificial sensory systems. The authors begin with the requirements of artificial sensory elements and then present an in-depth review of such elements demonstrated by memristive devices. Finally, the major challenges and opportunities in the development of memristor-based artificial sensory systems are discussed.

Diverse long-term potentiation and depression based on multilevel LiSiOxmemristor for neuromorphic computing

Memristor-based neuromorphic computing is expected to overcome the bottleneck of von Neumann architecture. An artificial synaptic device with continuous conductance variation is essential for implementing bioinspired neuromorphic systems. In this work, a memristor based on Pt/LiSiOx/TiN structure is developed to emulate an artificial synapse, which shows non-volatile multilevel resistance state memory behavior. Moreover, the high nonlinearity caused by abrupt changes in the set process is optimized by adjusting the initial resistance. 100 levels of continuously modulated conductance states are achieved and the nonlinearity factors are reduced to 1.31. The significant improvement is attributed to the decrease in the Schottky barrier height and the evolution of the conductive filaments. Finally, due to the improved linearity of the long-term potentiation/long-term depression behaviors in LiSiOxmemristor, a robust recognition rate (∼94.58%) is achieved for pattern recognition with the modified National Institute of Standards and Technology handwriting database. The Pt/LiSiOx/TiN memristor shows significant potential in high-performance multilevel data storage and neuromorphic computing systems.

Mimicking biological synapses with a-HfSiOx-based memristor: implications for artificial intelligence and memory applications

Memristors, owing to their uncomplicated structure and resemblance to biological synapses, are predicted to see increased usage in the domain of artificial intelligence. Additionally, to augment the capacity for multilayer data storage in high-density memory applications, meticulous regulation of quantized conduction with an extremely low transition energy is required. In this work, an a-HfSiOx-based memristor was grown through atomic layer deposition (ALD) and investigated for its electrical and biological properties for use in multilevel switching memory and neuromorphic computing systems. The crystal structure and chemical distribution of the HfSiOx/TaN layers were analyzed using X-ray diffraction (XRD) and X-ray photoelectron spectroscopy (XPS), respectively. The Pt/a-HfSiOx/TaN memristor was confirmed by transmission electron microscopy (TEM) and showed analog bipolar switching behavior with high endurance stability (1000 cycles), long data retention performance (104 s), and uniform voltage distribution. Its multilevel capability was demonstrated by restricting current compliance (CC) and stopping the reset voltage. The memristor exhibited synaptic properties, such as short-term plasticity, excitatory postsynaptic current (EPSC), spiking-rate-dependent plasticity (SRDP), post-tetanic potentiation (PTP), and paired-pulse facilitation (PPF). Furthermore, it demonstrated 94.6% pattern accuracy in neural network simulations. Thus, a-HfSiOx-based memristors have great potential for use in multilevel memory and neuromorphic computing systems.

A Self-Rectifying Synaptic Memristor Array with Ultrahigh Weight Potentiation Linearity for a Self-Organizing-Map Neural Network

Two-terminal self-rectifying (SR)-synaptic memristors are preeminent candidates for high-density and efficient neuromorphic computing, especially for future three-dimensional integrated systems, which can self-suppress the sneak path current in crossbar arrays. However, SR-synaptic memristors face the critical challenges of nonlinear weight potentiation and steep depression, hindering their application in conventional artificial neural networks (ANNs). Here, a SR-synaptic memristor (Pt/NiO_x/WO_3-x:Ti/W) and cross-point array with sneak path current suppression features and ultrahigh-weight potentiation linearity up to 0.9997 are introduced. The image contrast enhancement and background filtering are demonstrated on the basis of the device array. Moreover, an unsupervised self-organizing map (SOM) neural network is first developed for orientation recognition with high recognition accuracy (0.98) and training efficiency and high resilience toward both noises and steep synaptic depression. These results solve the challenges of SR memristors in the conventional ANN, extending the possibilities of large-scale oxide SR-synaptic arrays for high-density, efficient, and accurate neuromorphic computing.

Effect of Y-doping on switching mechanisms and impedance spectroscopy of HfOx-based RRAM devices

Y-doping can effectively improve the performance of HfO_x-based resistive random-access memory (RRAM) devices, but the underlying physical mechanism of Y-doping affecting the performance of HfO_x-based memristors is still missing and unclear. Although impedance spectroscopy (IS) has been widely used to investigate impedance characteristics and switching mechanisms of RRAM devices, there is less IS analysis on Y-doped HfO_x-based RRAM devices as well as devices at different temperatures. Here, the effect of Y-doping on the switching mechanism of HfO_x-based RRAM devices with a Ti/HfO_x/Pt structure were reported using current-voltage characteristics and IS. The results indicated that doping Y into HfO_xfilms could decrease the forming/operate voltage and improve the RS uniform. Both doped and undoped HfO_x-based RRAM devices obeyed the oxygen vacancies (V_O) conductive filament model along the grain boundary (GB). Additionally, the GB resistive activation energy of the Y-doped device was inferior to that of the undoped device. It exhibited a shift of theV_Otrap level towards the conduction band bottom after Y-doping in the HfO_xfilm, which was the main reason for the improved RS performance.

All oxide based flexible multi-folded invisible synapse as vision photo-receptor

All oxide-based transparent flexible memristor is prioritized for the potential application in artificially simulated biological optoelectronic synaptic devices. SnOx memristor with HfOx layer is found to enable a significant effect on synaptic properties. The memristor exhibits good reliability with long retention, 104 s, and high endurance, 104 cycles. The optimized 6 nm thick HfOx layer in SnOx-based memristor possesses the excellent synaptic properties of stable 350 epochs training, multi-level conductance (MLC) behaviour, and the nonlinearity of 1.53 and 1.46 for long-term potentiation and depression, respectively, and faster image recognition accuracy of 100% after 23 iterations. The maximum weight changes of -73.12 and 79.91% for the potentiation and depression of the synaptic device, respectively, are observed from the spike-timing-dependent plasticity (STDP) characteristics making it suitable for biological applications. The flexibility of the device on the PEN substrate is confirmed by the acceptable change of nonlinearities up to 4 mm bending. Such a synaptic device is expected to be used as a vision photo-receptor.

Multilayer redox-based HfOx/Al2O3/TiO2 memristive structures for neuromorphic computing

Redox-based memristive devices have shown great potential for application in neuromorphic computing systems. However, the demands on the device characteristics depend on the implemented computational scheme and unifying the desired properties in one stable device is still challenging. Understanding how and to what extend the device characteristics can be tuned and stabilized is crucial for developing application specific designs. Here, we present memristive devices with a functional trilayer of HfOx/Al2O3/TiO2 tailored by the stoichiometry of HfOx (x = 1.8, 2) and the operating conditions. The device properties are experimentally analyzed, and a physics-based device model is developed to provide a microscopic interpretation and explain the role of the Al2O3 layer for a stable performance. Our results demonstrate that the resistive switching mechanism can be tuned from area type to filament type in the same device, which is well explained by the model: the Al2O3 layer stabilizes the area-type switching mechanism by controlling the formation of oxygen vacancies at the Al2O3/HfOx interface with an estimated formation energy of ≈ 1.65 ± 0.05 eV. Such stabilized area-type devices combine multi-level analog switching, linear resistance change, and long retention times (≈ 107-108 s) without external current compliance and initial electroforming cycles. This combination is a significant improvement compared to previous bilayer devices and makes the devices potentially interesting for future integration into memristive circuits for neuromorphic applications.

Effect of Post-Annealing on Barrier Modulations in Pd/IGZO/SiO2/p+-Si Memristors

In this article, we study the post-annealing effect on the synaptic characteristics in Pd/IGZO/SiO₂/p⁺-Si memristor devices. The O-H bond in IGZO films affects the switching characteristics that can be controlled by the annealing process. We propose a switching model based on using a native oxide as the Schottky barrier. The barrier height is extracted by the conduction mechanism of thermionic emission in samples with different annealing temperatures. Additionally, the change in conductance is explained by an energy band diagram including trap models. The activation energy is obtained by the depression curve of the samples with different annealing temperatures to better understand the switching mechanism. Moreover, our results reveal that the annealing temperature and retention can affect the linearity of potentiation and depression. Finally, we investigate the effect of the annealing temperature on the recognition rate of MNIST in the proposed neural network.

Biopolymer based artificial synapses enable linear conductance tuning and low-power for neuromorphic computing

Neuromorphic computing is considered a promising method for resolving the traditional von Neumann bottleneck. Natural biomaterial-based artificial synapses are popular units for constructing neuromorphic computing systems while suffering from poor linearity and limited conduction states. In this work, a AgNO₃ doped iota-carrageenan (ι-car) based memristor is proposed to resolve the non-linear limitation. The memristor presents linear conductance tuning with a higher endurance (∼10⁴), more enriched conduction states (>2000), and much lower power consumption (∼3.6 μW) than previously reported biomaterial-based analog memristors. AgNO₃ is doped to ι-car to suppress the formation of Ag filaments, thereby eliminating uneven Joule heating. Using deep learning of hand-written digits as an application, a doping-enhanced recognition accuracy (93.8%) is achieved, close to that of an ideal synaptic device (95.7%). This work verifies the feasibility of using biopolymers for future high-performance computational and wearable/implantable electronic applications.

Biocompatible Casein Electrolyte-Based Electric-Double-Layer for Artificial Synaptic Transistors

In this study, we proposed a synaptic transistor using an emerging biocompatible organic material, namely, the casein electrolyte as an electric-double-layer (EDL) in the transistor. The frequency-dependent capacitance of the indium-tin-oxide (ITO)/casein electrolyte-based EDL/ITO capacitor was assessed. As a result, the casein electrolyte was identified to exhibit a large capacitance of ~1.74 μF/cm2 at 10 Hz and operate as an EDL owing to the internal proton charge. Subsequently, the implementation of synaptic functions was verified by fabricating the synaptic transistors using biocompatible casein electrolyte-based EDL. The excitatory post-synaptic current, paired-pulse facilitation, and signal-filtering functions of the transistors demonstrated significant synaptic behavior. Additionally, the spike-timing-dependent plasticity was emulated by applying the pre- and post-synaptic spikes to the gate and drain, respectively. Furthermore, the potentiation and depression characteristics modulating the synaptic weight operated stably in repeated cycle tests. Finally, the learning simulation was conducted using the Modified National Institute of Standards and Technology datasets to verify the neuromorphic computing capability; the results indicate a high recognition rate of 90%. Therefore, our results indicate that the casein electrolyte is a promising new EDL material that implements artificial synapses for building environmental and biologically friendly neuromorphic systems.

Discrete Memristor and Discrete Memristive Systems

In this paper, we investigate the mathematical models of discrete memristors based on Caputo fractional difference and G-L fractional difference. Specifically, the integer-order discrete memristor is a special model of those two cases. The "∞"-type hysteresis loop curves are observed when input is the bipolar periodic signal. Meanwhile, numerical analysis results show that the area of hysteresis decreases with the increase of frequency of input signal and the decrease of derivative order. Moreover, the memory effect, characteristics and physical realization of the discrete memristors are discussed, and a discrete memristor with short memory effects is designed. Furthermore, discrete memristive systems are designed by introducing the fractional-order discrete memristor and integer-order discrete memristor to the Sine map. Chaos is found in the systems, and complexity of the systems is controlled by the parameter of the memristor. Finally, FPGA digital circuit implementation is carried out for the integer-order and fractional-order discrete memristor and discrete memristive systems, which shows the potential application value of the discrete memristor in the engineering application field.

Variance-aware weight quantization of multi-level resistive switching devices based on Pt/LaAlO3/SrTiO3 heterostructures

Resistive switching devices have been regarded as a promising candidate of multi-bit memristors for synaptic applications. The key functionality of the memristors is to realize multiple non-volatile conductance states with high precision. However, the variation of device conductance inevitably causes the state-overlap issue, limiting the number of available states. The insufficient number of states and the resultant inaccurate weight quantization are bottlenecks in developing practical memristors. Herein, we demonstrate a resistive switching device based on Pt/LaAlO₃/SrTiO₃ (Pt/LAO/STO) heterostructures, which is suitable for multi-level memristive applications. By redistributing the surface oxygen vacancies, we precisely control the tunneling of two-dimensional electron gas (2DEG) through the ultrathin LAO barrier, achieving multiple and tunable conductance states (over 27) in a non-volatile way. To further improve the multi-level switching performance, we propose a variance-aware weight quantization (VAQ) method. Our simulation studies verify that the VAQ effectively reduces the state-overlap issue of the resistive switching device. We also find that the VAQ states can better represent the normal-like data distribution and, thus, significantly improve the computing accuracy of the device. Our results provide valuable insight into developing high-precision multi-bit memristors based on complex oxide heterostructures for neuromorphic applications.

Robust and Low-Power-Consumption Black Phosphorus-Graphene Artificial Synaptic Devices

Two-dimensional (2D) black phosphorus (BP) materials, as the most promising building blocks for the development of artificial synapses, have attracted more and more attention. However, the instability of exfoliated 2D BP structures still remains a problem in the development of artificial synapse devices. In this study, the robust and low-power-consumption artificial-synaptic-based BP was successfully manufactured. The synapse devices have high stability in the air atmosphere and do not show obvious degradation over 3 months. The obtained devices not only implement the main function of synapses but also perform the function of dendritic neural synapses and simple logical operations, revealing their very strong learning behavior. The high mobility of 2D BP as well as the coupled effect and quantum confinement effect of the graphene oxide quantum dot (GOQD) can greatly boost the performance of BP-based synapse devices, such as low power consumption (62 pW) and high sensitivity (ultrasmall stimuli at an amplitude of -20 mV). Moreover, benefiting from the GOQD and the interaction between BP and graphene, the main dominated mechanism of the BP-graphene synapse device can be the capture and release of electrons by the 2D BP and GOQD instead of the conductive filament.

Conductance Quantization Behavior in Pt/SiN/TaN RRAM Device for Multilevel Cell

In this work, we fabricated a Pt/SiN/TaN memristor device and characterized its resistive switching by controlling the compliance current and switching polarity. The chemical and material properties of SiN and TaN were investigated by X-ray photoelectron spectroscopy. Compared with the case of a high compliance current (5 mA), the resistive switching was more gradual in the set and reset processes when a low compliance current (1 mA) was applied by DC sweep and pulse train. In particular, low-power resistive switching was demonstrated in the first reset process, and was achieved by employing the negative differential resistance effect. Furthermore, conductance quantization was observed in the reset process upon decreasing the DC sweep speed. These results have the potential for multilevel cell (MLC) operation. Additionally, the conduction mechanism of the memristor device was investigated by I-V fitting.

Multi-Level Resistive Switching of Pt/HfO2/TaN Memory Device

This work characterizes resistive switching and neuromorphic simulation of Pt/HfO2/TaN stack as an artificial synaptic device. A stable bipolar resistive switching operation is performed by repetitive DC sweep cycles. Furthermore, endurance (DC 100 cycles) and retention (5000 s) are demonstrated for reliable resistive operation. Low-resistance and high-resistance states follow the Ohmic conduction and Poole–Frenkel emission, respectively, which is verified through the fitting process. For practical operation, the set and reset processes are performed through pulses. Further, potentiation and depression are demonstrated for neuromorphic application. Finally, neuromorphic system simulation is performed through a neural network for pattern recognition accuracy of the Fashion Modified National Institute of Standards and Technology dataset.

Analog Synaptic Transistor with Al-Doped HfO2 Ferroelectric Thin Film

Neuromorphic computing has garnered significant attention because it can overcome the limitations of the current von-Neumann computing system. Analog synaptic devices are essential for realizing hardware-based artificial neuromorphic devices; however, only a few systematic studies in terms of both synaptic materials and device structures have been conducted so far, and thus, further research is required in this direction. In this study, we demonstrate the synaptic characteristics of a ferroelectric material-based thin-film transistor (FeTFT) that uses partial switching of ferroelectric polarization to implement analog conductance modulation. For a ferroelectric material, an aluminum-doped hafnium oxide (Al-doped HfO2) thin film was prepared by atomic layer deposition. As an analog synaptic device, our FeTFT successfully emulated short-term plasticity and long-term plasticity characteristics, such as paired-pulse facilitation and spike timing-dependent plasticity. In addition, we obtained potentiation/depression weight updates with high linearity, an on/off ratio, and low cycle-to-cycle variation by adjusting the amplitude and number of input pulses. In the simulation trained with optimized potentiation/depression conditions, we achieved a pattern recognition accuracy of approximately 90% for the Modified National Institute of Standard and Technology (MNIST) handwritten data set. Our results indicated that ferroelectric transistors can be used as an alternative artificial synapse.

Stimuli-Responsive Memristive Materials for Artificial Synapses and Neuromorphic Computing

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.

Demonstration of Threshold Switching and Bipolar Resistive Switching in Ag/SnOx/TiN Memory Device

In this work, we observed the duality of threshold switching and non-volatile memory switching of Ag/SnOx/TiN memory devices by controlling the compliance current (CC) or pulse amplitude. The insulator thickness and chemical analysis of the device stack were confirmed by transmission electron microscope (TEM) images of the Ag/SnOx/TiN stack and X-ray photoelectron spectroscopy (XPS) of the SnOx film. The threshold switching was achieved at low CC (50 μA), showing volatile resistive switching. Optimal CC (5 mA) for bipolar resistive switching conditions with a gradual transition was also found. An unstable low-resistance state (LRS) and negative-set behavior were observed at CCs of 1 mA and 30 mA, respectively. We also demonstrated the pulse operation for volatile switching, set, reset processes, and negative-set behaviors by controlling pulse amplitude and polarity. Finally, the potentiation and depression characteristics were mimicked by multiple pulses, and MNIST pattern recognition was calculated using a neural network, including the conductance update for a hardware-based neuromorphic system.

Gradually Modified Conductance in the Self-Compliance Region of an Atomic-Layer-Deposited Pt/TiO2/HfAlOx/TiN RRAM Device

This study presents conductance modulation in a Pt/TiO2/HfAlOx/TiN resistive memory device in the compliance region for neuromorphic system applications. First, the chemical and material characteristics of the atomic-layer-deposited films were verified by X-ray photoelectron spectroscopy depth profiling. The low-resistance state was effectively controlled by the compliance current, and the high-resistance state was adjusted by the reset stop voltage. Stable endurance and retention in bipolar resistive switching were achieved. When a compliance current of 1 mA was imposed, only gradual switching was observed in the reset process. Self-compliance was used after an abrupt set transition to achieve a gradual set process. Finally, 10 cycles of long-term potentiation and depression were obtained in the compliance current region for neuromorphic system applications.

Temporal State Machines: Using Temporal Memory to Stitch Time-based Graph Computations

Race logic, an arrival-time-coded logic family, has demonstrated energy and performance improvements for applications ranging from dynamic programming to machine learning. However, the various ad hoc mappings of algorithms into hardware rely on researcher ingenuity and result in custom architectures that are difficult to systematize. We propose to associate race logic with the mathematical field of tropical algebra, enabling a more methodical approach toward building temporal circuits. This association between the mathematical primitives of tropical algebra and generalized race logic computations guides the design of temporally coded tropical circuits. It also serves as a framework for expressing high-level timing-based algorithms. This abstraction, when combined with temporal memory, allows for the systematic exploration of race logic-based temporal architectures by making it possible to partition feed-forward computations into stages and organize them into a state machine. We leverage analog memristor-based temporal memories to design such a state machine that operates purely on time-coded wavefronts. We implement a version of Dijkstra's algorithm to evaluate this temporal state machine. This demonstration shows the promise of expanding the expressibility of temporal computing to enable it to deliver significant energy and throughput advantages.

Hybrid oxide brain-inspired neuromorphic devices for hardware implementation of artificial intelligence

The state-of-the-art artificial intelligence technologies mainly rely on deep learning algorithms based on conventional computers with classical von Neumann computing architectures, where the memory and processing units are separated resulting in an enormous amount of energy and time consumed in the data transfer process. Inspired by the human brain acting like an ultra-highly efficient biological computer, neuromorphic computing is proposed as a technology for hardware implementation of artificial intelligence. Artificial synapses are the main component of a neuromorphic computing architecture. Memristors are considered to be a relatively ideal candidate for artificial synapse applications due to their high scalability and low power consumption. Oxides are most widely used in memristors due to the ease of fabrication and high compatibility with complementary metal-oxide-semiconductor processes. However, oxide memristors suffer from unsatisfactory stability and reliability. Oxide-based hybrid structures can effectively improve the device stability and reliability, therefore providing a promising prospect for the application of oxide memristors to neuromorphic computing. This work reviews the recent advances in the development of hybrid oxide memristive synapses. The discussion is organized according to the blending schemes as well as the working mechanisms of hybrid oxide memristors.

Engineering Method for Tailoring Electrical Characteristics in TiN/TiOx/HfOx/Au Bi-Layer Oxide Memristive Devices

Memristive devices have led to an increased interest in neuromorphic systems. However, different device requirements are needed for the multitude of computation schemes used there. While linear and time-independent conductance modulation is required for machine learning, non-linear and time-dependent properties are necessary for neurobiologically realistic learning schemes. In this context, an adaptation of the resistance switching characteristic is necessary with regard to the desired application. Recently, bi-layer oxide memristive systems have proven to be a suitable device structure for this purpose, as they combine the possibility of a tailored memristive characteristic with low power consumption and uniformity of the device performance. However, this requires technological solutions that allow for precise adjustment of layer thicknesses, defect densities in the oxide layers, and suitable area sizes of the active part of the devices. For this purpose, we have investigated the bi-layer oxide system TiN/TiOx/HfOx/Au with respect to tailored I-V non-linearity, the number of resistance states, electroforming, and operating voltages. Therefore, a 4-inch full device wafer process was used. This process allows a systematic investigation, i.e., the variation of physical device parameters across the wafer as well as a statistical evaluation of the electrical properties with regard to the variability from device to device and from cycle to cycle. For the investigation, the thickness of the HfOx layer was varied between 2 and 8 nm, and the size of the active area of devices was changed between 100 and 2,500 µm2. Furthermore, the influence of the HfOx deposition condition was investigated, which influences the conduction mechanisms from a volume-based, filamentary to an interface-based resistive switching mechanism. Our experimental results are supported by numerical simulations that show the contribution of the HfOx film in the bi-layer memristive system and guide the development of a targeting device.

Spiking Neural Network (SNN) With Memristor Synapses Having Non-linear Weight Update

Among many artificial neural networks, the research on Spike Neural Network (SNN), which mimics the energy-efficient signal system in the brain, is drawing much attention. Memristor is a promising candidate as a synaptic component for hardware implementation of SNN, but several non-ideal device properties are making it challengeable. In this work, we conducted an SNN simulation by adding a device model with a non-linear weight update to test the impact on SNN performance. We found that SNN has a strong tolerance for the device non-linearity and the network can keep the accuracy high if a device meets one of the two conditions: 1. symmetric LTP and LTD curves and 2. positive non-linearity factors for both LTP and LTD. The reason was analyzed in terms of the balance between network parameters as well as the variability of weight. The results are considered to be a piece of useful prior information for the future implementation of emerging device-based neuromorphic hardware.

Multi-Level Analog Resistive Switching Characteristics in Tri-Layer HfO2/Al2O3/HfO2 Based Memristor on ITO Electrode

Atomic layer deposited (ALD) HfO2/Al2O3/HfO2 tri-layer resistive random access memory (RRAM) structure has been studied with a transparent indium tin oxide (ITO) transparent electrode. Highly stable and reliable multilevel conductance can be controlled by the set current compliance and reset stop voltage in bipolar resistive switching. Improved gradual resistive switching was achieved because of the interdiffusion in the HfO2/Al2O3 interface where tri-valent Al incorporates with HfO2 and produces HfAlO. The uniformity in bipolar resistive switching with Ion/Ioff ratio (>10) and excellent endurance up to >103 cycles was achieved. Multilevel conductance levels in potentiation/depression were realized with constant amplitude pulse train and increasing pulse amplitude. Thus, tri-layer structure-based RRAM can be a potential candidate for the synaptic device in neuromorphic computing.

Comparison of diverse resistive switching characteristics and demonstration of transitions among them in Al-incorporated HfO2-based resistive switching memory for neuromorphic applications

Diverse resistive switching behaviors are observed in the Pt/HfAlO_x/TiN memory device depending on the compliance current, the sweep voltage amplitude, and the bias polarity. We extensively compare three types of resistive switching characteristics in a Pt/HfAlO_x/TiN device in terms of endurance, ON/OFF ratio, linear conductance update, and read margin in a cross-point array structure for synaptic device applications. The bipolar resistive switching under positive set and negative reset shows better linear synaptic weight updates due to gradual switching than the bipolar resistive switching at the opposite polarity. The complementary resistive switching shows a higher read margin due to the current suppression at a low voltage regime. In addition, the potentiation and the depression can be adjusted at the same voltage polarity for a hardware neuromorphic system. Finally, we demonstrate the transition between bipolar resistive switching and complementary resistive switching, which could provide flexibility for different applications.

Diverse resistive switching behaviors are observed in the Pt/HfAlO_x/TiN memory device depending on the compliance current, the sweep voltage amplitude, and the bias polarity.