Search

Reservoir computing (RC) possesses a simple architecture and high energy efficiency for time‐series data analysis through machine learning algorithms. To date, RC has evolved into several innovative variants. The next generation reservoir computing (NGRC) variant, founded on nonlinear vector autoregression (NVAR) distinguishes itself due to its fewer hyperparameters and independence from physical random connection matrices, while yielding comparable results. However, NGRC networks struggle with massive Kronecker product calculations and matrix‐vector multiplications within the read out layer, leading to substantial efficiency challenges for traditional von Neumann architectures. In this work, a hybrid digital‐analog hardware system tailored for NGRC is developed. The digital part is a Kronecker product calculation unit with data filtering, which realizes transformation of nonlinear vector of the input linear vector. For matrix‐vector multiplication, a computing‐in‐memory architecture based on resistive random access memory array offers an energy‐efficient hardware solution, which markedly reduces data transfer and greatly improve computational parallelism and energy efficiency. The predictive capabilities of this hybrid NGRC system are validated through the Lorenz63 model, achieving a normalized root mean square error (NRMSE) of 0.00098 and an energy efficiency of 19.42TOPS W−1. [ABSTRACT FROM AUTHOR]

In this study, a two-dimensional electron gas (2DEG), which is a conductive layer formed at the interface of Al2O3 and TiO2, was used as an electrode for resistive random access memory (RRAM) and implemented in a cell size down to 30 nm. For an RRAM device comprising W/2DEG/TiO2/W, we confirmed that the dominant switching mechanism changed from interfacial to filamentary as the cell size decreased from 500 nm to 30 nm. Through analyses of changes in forming characteristics and conduction mechanisms in the low resistive state depending on the cell size, it was identified that the 2DEG acted as an oxygen-scavenging layer of TiO2 during the resistive switching process. By comparing the switching characteristics of RRAM devices with and without 2DEG for a 30 nm cell size, we confirmed that a high-performance 2DEG RRAM was realized, with highly uniform current–voltage characteristics, a low operating voltage (∼1 V), and a high on/off ratio (>102). Finally, the applicability of the proposed device to a crossbar array was validated by evaluating 1S1R operation with an NbO2-based selector. Considering the improved switching uniformity, the 2DEG RRAM shows promise for high-density memory applications. [ABSTRACT FROM AUTHOR]

Reservoir computing (RC) possesses a simple architecture and high energy efficiency for time‐series data analysis through machine learning algorithms. To date, RC has evolved into several innovative variants. The next generation reservoir computing (NGRC) variant, founded on nonlinear vector autoregression (NVAR) distinguishes itself due to its fewer hyperparameters and independence from physical random connection matrices, while yielding comparable results. However, NGRC networks struggle with massive Kronecker product calculations and matrix‐vector multiplications within the read out layer, leading to substantial efficiency challenges for traditional von Neumann architectures. In this work, a hybrid digital‐analog hardware system tailored for NGRC is developed. The digital part is a Kronecker product calculation unit with data filtering, which realizes transformation of nonlinear vector of the input linear vector. For matrix‐vector multiplication, a computing‐in‐memory architecture based on resistive random access memory array offers an energy‐efficient hardware solution, which markedly reduces data transfer and greatly improve computational parallelism and energy efficiency. The predictive capabilities of this hybrid NGRC system are validated through the Lorenz63 model, achieving a normalized root mean square error (NRMSE) of 0.00098 and an energy efficiency of 19.42TOPS W−1.

Herein, a digital–analog hybrid resistive random‐access memory (RRAM) is prepared by integrating the structurally similar SiNx‐based digital‐type RRAM with analog‐type RRAM by heterogeneous integration method. The Pt/SiNx/Ta/Ru is a digital RRAM due to the formation and breakage of the internal silicon dangling bonds conductive filaments, and the TiN/SiNx/Ta/Ru structure is an analog RRAM due to the traps‐filled limit region of the space‐charge limited current. The heterogeneously integrated digital RRAM has good cycling stability and endurance characteristics, and the heterogeneously integrated analog RRAM has high linearity and multistate counting characteristics. This heterogeneous integration approach is useful for the implementation of hybrid digital–analog RRAM. [ABSTRACT FROM AUTHOR]

In this work, a machine learning‐assisted prediction model is proposed to analyze the reliability issues in the 28 nm resistive random access memory (RRAM) chip with raw data measured from RRAM test chip. The neural network of long‐short time memory (LSTM) is trained by the voltages and resistance during the endurance test (input vectors) and generates the output of the dichotomy states with a satisfied testing result >83.08%. According to the prediction results, the "real fail" state or "fake fail" state of the devices can get in the future. By collaborating with a well‐designed resurrection algorithm (RA), the percentage of real and fake failed cells dropped by 35% and 29%, respectively. Besides, the tail bits in retention significantly reduced from 33% to 14.6% due to the reduction of oxygen vacancies in the gaps of conducting filaments by applying ten consecutive cycles of RA. This intelligent prediction and repair module can prolong the lifetime of RRAM chips effectively in practical applications. [ABSTRACT FROM AUTHOR]

A novel benzothiadiazole-based donor-acceptor type polymer, resistive random access memory (RRAM) material, poly{[4,4'-(2,7-diphenyl-9H-fluorene-9,9-diyl)bis(N,N-diphenylaniline)]-alt-[4,7-bis(4-dodecyl-5-vinylthiophen-2- yl)benzo[c][1,2,5] thiadiazole]} (PFVT) was synthesized. By using PFVT as the active layer, the as-fabricated electronic device with a configuration of Al/PFVT/ITO (ITO: indium tin oxides) exhibites a nonvolatile RRAM performance. During 50 consecutive cycle-to-cycle measurements, the observed average switch-on voltage, switch-off voltage and ON/OFF current ratio are (−0.54 ± 0.01) V, (2.42 ± 0.05) V, and 1.5×10³, respectively. The cycle-to-cycle variation for the programming voltage is less than 2.1%, suggesting excellent reliability. After thermal annealing at 200 ℃, the switch-on and switch-off voltages decrease to (−0.49±0.01) V and (2.27±0.02) V, respectively, due to the enhanced material crystallinity. The switching mechanism can be assigned to the intramolecular charge-transfer occurred in the materials system. The ON and OFF-state currents can be fitted by the Ohmic current model and space-charge-limited current model, respectively. The switchon voltage is highly associated with the bandgap of the materials. For comparison purpose, 4,4′-(2,7-diphenyl-9H-fluorene-9,9- diyl)bis(N,N-diphenylaniline) was replaced with phenyl group to synthesize poly[4-(4-dodecyl-5-((E)-4- methylstyryl)thiophen-2-yl)-7-(4-dodecyl-5-((E)-prop-1-en-1-yl)thiophen-2-yl)benzo[c][1,2,5]thiadiazole](PPVT). In contrast to PFVT, PPVT also shows the similar RRAM performance, with a bigger switch-on voltage and a smaller ON/OFF current ratio. Replacement of bulky fluorene unit with phenyl unit leads to a sharp decrease in the thermal stability of the material and an increase in the bandgap. [ABSTRACT FROM AUTHOR]

This article investigates resistive random access memory (ReRAM) crossbar memory arrays, which is a notable development in non-volatile memory technology. We highlight ReRAM's competitive edge over NAND, NOR Flash, and phase-change memory (PCM), particularly in terms of endurance, speed, and energy efficiency. This paper focuses on the architecture of crossbar arrays, where memristive devices are positioned at intersecting metal wires. We emphasize the unique resistive switching mechanisms of memristors and the challenges of sneak path currents and delve into the roles and configurations of selectors, particularly focusing on the one-selector one-resistor (1S1R) architecture with an insulator–metal transition (IMT) based selector. We use SPICE simulations based on defined models to examine a 3 × 3 1S1R ReRAM array with vanadium dioxide selectors and titanium dioxide film memristors, assessing the impact of ambient temperature and critical IMT temperatures on array performance. We highlight the operational regions of low resistive state (LRS) and high resistive state (HRS), providing insights into the electrical behavior of these components under various conditions. Lastly, we demonstrate the impact of selector presence on sneak path currents. This research contributes to the overall understanding of ReRAM crossbar arrays integrated with IMT material-based selectors. [ABSTRACT FROM AUTHOR]

This article investigates resistive random access memory (ReRAM) crossbar memory arrays, which is a notable development in non-volatile memory technology. We highlight ReRAM’s competitive edge over NAND, NOR Flash, and phase-change memory (PCM), particularly in terms of endurance, speed, and energy efficiency. This paper focuses on the architecture of crossbar arrays, where memristive devices are positioned at intersecting metal wires. We emphasize the unique resistive switching mechanisms of memristors and the challenges of sneak path currents and delve into the roles and configurations of selectors, particularly focusing on the one-selector one-resistor (1S1R) architecture with an insulator–metal transition (IMT) based selector. We use SPICE simulations based on defined models to examine a 3 × 3 1S1R ReRAM array with vanadium dioxide selectors and titanium dioxide film memristors, assessing the impact of ambient temperature and critical IMT temperatures on array performance. We highlight the operational regions of low resistive state (LRS) and high resistive state (HRS), providing insights into the electrical behavior of these components under various conditions. Lastly, we demonstrate the impact of selector presence on sneak path currents. This research contributes to the overall understanding of ReRAM crossbar arrays integrated with IMT material-based selectors.

Diabetic retinopathy (DR) is a leading cause of permanent vision loss worldwide. It refers to irreversible retinal damage caused due to elevated glucose levels and blood pressure. Regular screening for DR can facilitate its early detection and timely treatment. Neural network-based DR classifiers can be leveraged to achieve such screening in a convenient and automated manner. However, these classifiers suffer from reliability issue where they exhibit strong performance during development but degraded performance after deployment. Moreover, they do not provide supplementary information about the prediction outcome, which severely limits their widespread adoption. Furthermore, energy-efficient deployment of these classifiers on edge devices remains unaddressed, which is crucial to enhance their global accessibility. In this paper, we present a reliable and energy-efficient hardware for DR detection, suitable for deployment on edge devices. We first develop a DR classification model using custom training data that incorporates diverse image quality and image sources along with improved class balance. This enables our model to effectively handle both on-field variations in retinal images and minority DR classes, enhancing its post-deployment reliability. We then propose a pseudo-binary classification scheme to further improve the model performance and provide supplementary information about the model prediction. Additionally, we present an energy-efficient hardware design for our model using memristor-based computation-in-memory, to facilitate its deployment on edge devices. Our proposed approach achieves reliable DR classification with three orders of magnitude reduction in energy consumption over state-of-the-art hardware platforms.

Analog memory presents a promising solution in the face of the growing demand for energy-efficient artificial intelligence (AI) at the edge. In this study, we demonstrate efficient deep neural network transfer learning utilizing hardware and algorithm co-optimization in an analog resistive random-access memory (ReRAM) array. For the first time, we illustrate that in open-loop deep neural network (DNN) transfer learning for image classification tasks, convergence rates can be accelerated by approximately 3.5 times through the utilization of cooptimized analog ReRAM hardware and the hardware-aware Tiki-Taka v2 (TTv2) algorithm. A simulation based on statistical 14 nm CMOS ReRAM array data provides insights into the performance of transfer learning on larger network workloads, exhibiting notable improvement over conventional training with random initialization. This study shows that analog DNN transfer learning using an optimized ReRAM array can achieve faster convergence with a smaller dataset compared to training from scratch, thus augmenting AI capability at the edge. [ABSTRACT FROM AUTHOR]

Covalent organic polymers (COPs) memristors with multilevel memory behavior in harsh environments and photoelectric regulation are crucial for high‐density storage and high‐efficiency neuromorphic computing. Here, a donor–acceptor (D–A)‐type COP film (Py‐COP‐3), which is initiated by keto–enol tautomerism, is proposed for high‐performance memristors. Satisfactorily, the indium tin oxide (ITO)/Py‐COP‐3/Ag device demonstrates multilevel memory performance, even in high temperatures, acid‐base corrosion, and various organic solvents. Moreover, the performance can be modulated by the photoelectric effect to maintain a great switching behavior. By contrast, Py‐COP‐0, with similar structure and chemical composition to Py‐COP‐3 but without keto–enol tautomerism, exhibits binary storage performance. Further studies unravel that both the formation of conductive filaments and charge transfer within D‐A Py‐COP‐3 film contribute to the resistive switching behavior of memory devices. [ABSTRACT FROM AUTHOR]

Abstract In this work, a machine learning‐assisted prediction model is proposed to analyze the reliability issues in the 28 nm resistive random access memory (RRAM) chip with raw data measured from RRAM test chip. The neural network of long‐short time memory (LSTM) is trained by the voltages and resistance during the endurance test (input vectors) and generates the output of the dichotomy states with a satisfied testing result >83.08%. According to the prediction results, the “real fail” state or “fake fail” state of the devices can get in the future. By collaborating with a well‐designed resurrection algorithm (RA), the percentage of real and fake failed cells dropped by 35% and 29%, respectively. Besides, the tail bits in retention significantly reduced from 33% to 14.6% due to the reduction of oxygen vacancies in the gaps of conducting filaments by applying ten consecutive cycles of RA. This intelligent prediction and repair module can prolong the lifetime of RRAM chips effectively in practical applications.

Analog memory presents a promising solution in the face of the growing demand for energy-efficient artificial intelligence (AI) at the edge. In this study, we demonstrate efficient deep neural network transfer learning utilizing hardware and algorithm co-optimization in an analog resistive random-access memory (ReRAM) array. For the first time, we illustrate that in open-loop deep neural network (DNN) transfer learning for image classification tasks, convergence rates can be accelerated by approximately 3.5 times through the utilization of co-optimized analog ReRAM hardware and the hardware-aware Tiki-Taka v2 (TTv2) algorithm. A simulation based on statistical 14 nm CMOS ReRAM array data provides insights into the performance of transfer learning on larger network workloads, exhibiting notable improvement over conventional training with random initialization. This study shows that analog DNN transfer learning using an optimized ReRAM array can achieve faster convergence with a smaller dataset compared to training from scratch, thus augmenting AI capability at the edge.

The coming big‐data era has created a huge demand for next‐generation memory technologies with characters of higher data‐storage densities, faster access speeds, lower power consumption and better environmental compatibility. In this field, the design of resistive switching active materials is pivotal but challengeable. Polyoxometalates (POMs) are promising candidates for next‐generation molecular memristors due to their versatile redox characters, excellent electron reservoirs and good compatibility/convenience in microelectronics processing. In this review, five kinds of POM‐based active materials in nonvolatile memories (inorganic POMs, crystalline organic‐inorganic hybrid POMOFs, polymer modified POMs, POM/transition metal oxides composites and the deposition of POM on metal surfaces) were described. The components of POMs active materials, device fabrications, device parameters, and resistive switching mechanisms relative to their structures were summarized. Finally, challenges and future perspectives of POMs‐based memristors were also presented. [ABSTRACT FROM AUTHOR]

Resistive switching devices are candidates to be used as weight for the future hardware realization of neuronal networks. Herein, these resistive switches base on oxygen vacancy migration and can be toggled between different resistance states. Internal processes lead to a variability over time in these states. To understand this, a dynamical model is developed, which links the internal physical mechanism to the current response. Thereby, the electronic current is calculated by tunneling processes over oxygen vacancies. The model allows to understand the physical transport properties and the current–voltage dependence. Integrating ionic hopping processes clarifies the variability in the electronic conduction. The derived model does not require empirical input parameters and only depends on the properties of the materials. This allows to use literature values and independently compare them to electrical measurements. The model predicts the experiments correctly. Thereupon, the physical properties of the conduction are investigated with respect to the transport over discrete energy levels, which change under the hopping of oxygen vacancies. Afterwards, the current level and variability are simulated for increasing oxygen vacancy concentrations to investigate analog switching, which is required for neuronal network layers. Finally, the variability is tested with multiple interacting cells in a neuronal layer. [ABSTRACT FROM AUTHOR]

Resistive switching devices are candidates to be used as weight for the future hardware realization of neuronal networks. Herein, these resistive switches base on oxygen vacancy migration and can be toggled between different resistance states. Internal processes lead to a variability over time in these states. To understand this, a dynamical model is developed, which links the internal physical mechanism to the current response. Thereby, the electronic current is calculated by tunneling processes over oxygen vacancies. The model allows to understand the physical transport properties and the current–voltage dependence. Integrating ionic hopping processes clarifies the variability in the electronic conduction. The derived model does not require empirical input parameters and only depends on the properties of the materials. This allows to use literature values and independently compare them to electrical measurements. The model predicts the experiments correctly. Thereupon, the physical properties of the conduction are investigated with respect to the transport over discrete energy levels, which change under the hopping of oxygen vacancies. Afterwards, the current level and variability are simulated for increasing oxygen vacancy concentrations to investigate analog switching, which is required for neuronal network layers. Finally, the variability is tested with multiple interacting cells in a neuronal layer.

Activation energy, bipolar resistance switching behavior, and the electrical conduction transport properties of ITOX:SiO2 thin film resistive random access memory (RRAM) devices were observed and discussed. The ITOX:SiO2 thin films were prepared using a co-sputtering deposition method on the TiN/Si substrate. For the RRAM device structure fabrication, an Al/ITOX:SiO2/TiN/Si structure was prepared by using aluminum for the top electrode and a TiN material for the bottom electrode. In addition, grain growth, defect reduction, and RRAM device performance of the ITOX:SiO2 thin film for the various oxygen gas flow conditions were observed and described. Based on the I-V curve measurements of the RRAM devices, the turn on-off ratio and the bipolar resistance switching properties of the Al/ITOX:SiO2/TiN/Si RRAM devices in the set and reset states were also obtained. At low operating voltages and high resistance values, the conductance mechanism exhibits hopping conduction mechanisms for set states. Moreover, at high operating voltages, the conductance mechanism behaves as an ohmic conduction current mechanism. Finally, the Al/ITOX:SiO2/TiN/Si RRAM devices demonstrated memory window properties, bipolar resistance switching behavior, and nonvolatile characteristics for next-generation nonvolatile memory applications. [ABSTRACT FROM AUTHOR]

Variability is an inherent property of memristive devices based on the switching of resistance in a simple metal–oxide–metal structure compatible with the standard complementary metal–oxide–semiconductor fabrication process. For each specific structure, the variability should be measured and assessed as both the negative and positive factors for different applications of memristive devices. In this report, it is shown how this variability can be extracted and analyzed for such main parameters of resistive switching as the set and reset voltages/currents and how it depends on the methodology used and experimental conditions. The obtained results should be taken into account in the design and predictive simulation of memristive devices and circuits. [ABSTRACT FROM AUTHOR]

The electrode-dependent resistive random access memories (ReRAM) with aluminum, silver, platinum, and indium tin oxide (ITO) judiciously selected as a pair of electrodes, and the bismuth ferrite (BiFeO3 or BFO) as the active dielectric layer, are fabricated for elaborate characterizations. The Ag/BFO/Pt and Ag/BFO/ITO ReRAMs have reflected excellent electrical properties, notably for the Ag/BFO/ITO combination. The Ag/BFO/ITO endures more than 1200 switching cycles and an excellent (> 102) on/off current or resistance ratio. The retention time in both high and low resistance states could reach 104 s and beyond. It has been found that the electrochemical metallization mechanism dominated by metal ion migration and the valence change mechanism dictated by oxygen vacancy conduction are inseparable from the establishment and destruction of the conductive filament. Moreover, a ReRAM with a dual dielectric layer of BFO/α-Fe2O3) is also prepared for comparison. A special "two-step reset" phenomenon is observed which could be explained with filament theory. [ABSTRACT FROM AUTHOR]

The electrode-dependent resistive random access memories (ReRAM) with aluminum, silver, platinum, and indium tin oxide (ITO) judiciously selected as a pair of electrodes, and the bismuth ferrite (BiFeO3 or BFO) as the active dielectric layer, are fabricated for elaborate characterizations. The Ag/BFO/Pt and Ag/BFO/ITO ReRAMs have reflected excellent electrical properties, notably for the Ag/BFO/ITO combination. The Ag/BFO/ITO endures more than 1200 switching cycles and an excellent (> 102) on/off current or resistance ratio. The retention time in both high and low resistance states could reach 104 s and beyond. It has been found that the electrochemical metallization mechanism dominated by metal ion migration and the valence change mechanism dictated by oxygen vacancy conduction are inseparable from the establishment and destruction of the conductive filament. Moreover, a ReRAM with a dual dielectric layer of BFO/α-Fe2O3) is also prepared for comparison. A special "two-step reset" phenomenon is observed which could be explained with filament theory. [ABSTRACT FROM AUTHOR]

Woven resistive random access memory (RRAM) is a promising subject in flexible wearable electronic devices. In this work, polyvinylammonium iodate (PVAm·HI) is added to the FAPbI3 perovskite precursor solution to fabricate a flexible fibrous woven RRAM array by improving the flexibility and stability of FAPbI3 perovskite. The long carbochain polymer backbone of PVAm serves as nucleation sites and a growth template to improve the perovskite crystallization process, and to in situ crosslink the perovskite grains at the crystal interface. The functional Al@FAPbI3:PVAm fibers are then prepared by solution dip-coating to assemble the fibrous crosspoint RRAM device with the structure of Al@FAPbI3:PVAm/Al by crossing bare aluminum (Al) fibers with functional fibers. Compared to a pristine device, the PVAm-modified devices exhibit a considerable improvement in the ON/OFF ratio and environmental stability. Specifically, the 2% PVAm-modified FAPbI3 RRAM devices show an evident bipolar resistive switching (RS) behavior with a high ON/OFF ratio of 109, which can easily achieve multilevel storage by setting the compliance current (Icc) to increase the storage density in the crosspoint array. Interestingly, a 100-times bent plastics-encapsulated device still exhibits a good RS behavior. This work provides a facile approach to achieve high-density storage in flexible wearable electronic devices. [ABSTRACT FROM AUTHOR]

One of the most effective methods for improving the storage density of resistive random access memories (RRAMs) is to fabricate 3D vertical stacking devices. By using BP-DDAT(DDAT: S-1-dodecyl-S ′-(α,α′-dimethyl-α′ ′- aceticacid)trithiocarbonate) as a key 2D template and reversible addition-fragmentation chain transfer (RAFT) reagent, a novel poly(N-vinylcarbazole) covalently functionalized black phosphorus derivative (BP-PVK) is successfully synthesized and well-characterized by infrared spectroscopy, X-ray electron spectroscopy and UV-Vis absorption spectroscopy. The environmental stability and solubility of BP nanosheets are greatly improved. Using BP-PVK as active layer, a double-layer vertically stacked RRAM memory device (17×17 stripe array) with a configuration of Al/BP-PVK/Al/BP-PVK/Al is fabricated. The as-fabricated device shows good bistable electrical switching and non-volatile rewritable performance at room temperature, with an ON/OFF current ratio exceeding 10³, higher production yield of the memory devices and structural uniformity. [ABSTRACT FROM AUTHOR]

According to Moore's Law's development law, traditional floating gate memory is constrained by charge tunneling, and its size is approaching the physical limit, which is insufficient to meet the requirements of large data storage. The introduction of new information storage devices may be the key to overcoming the bottleneck. Resistive random access memory (RRAM) has garnered interest due to its fast switching speed, low power consumption, and high integration density. The resistive switching (RS) behaviors can be demonstrated in many materials, including transition metal oxides, perovskite oxides and organic matter, etc. Among these materials, graphene oxide (GO) with its unique physical, chemical properties and excellent mechanical properties is attracting significant attention for use in RRAM owing to its RS operation and potential for integration with other graphene-based electronics. However, there is unacceptable variability in RS reliability, including retention and endurance, which is the key factor that affects the development of memristors. In addition, the RS mechanism of GO-based RRAM has not been systematically discussed. In this article, we discuss systematically several typical models of the switching mechanism of GO-based RRAM and a summary of methods for improving the device's RS performance. This article concludes by discussing the applications of GO-RRAM in artificial neural networks, flexible devices, and biological monitoring. [ABSTRACT FROM AUTHOR]

Processing-in-memory (PIM) is a promising architecture to design various types of neural network accelerators as it ensures the efficiency of computation together with Resistive Random Access Memory (ReRAM). ReRAM has now become a promising solution to enhance computing efficiency due to its crossbar structure. In this paper, a ReRAM-based PIM neural network accelerator is addressed, and different kinds of methods and designs of various schemes are discussed. Various models and architectures implemented for a neural network accelerator are determined for research trends. Further, the limitations or challenges of ReRAM in a neural network are also addressed in this review. [ABSTRACT FROM AUTHOR]

With the increase in data-driven frameworks, the demand for non-volatile memory has increased and resistive switching-based memory is one of them. In this study, the structural, charge transport and the current vs. voltage (I-V) behaviour of (1-x)La 0.7 Sr 0.3 MnO 3 .(x)ZnO composite systems were investigated and observed that, they exhibit bipolar resistive switching behaviour. The oxygen vacancy, oxygen ions and interfacial layers play an important role in the resistive switching behaviour. From the XPS analysis, it is observed that the oxygen-deficient region increases with the increasing concentration of ZnO. The sample with x = 0.050 shows better resistive switching behaviour and high ON/OFF current ratio as compared with the x = 0.005 and 0.010 samples. The Ohmic and Schottky emissions are found to be responsible for the conduction mechanism. The shifting in the metal–insulator transition temperature (TMI) towards the low temperature is observed from the resistivity vs. temperature plot with the increasing concentration of the ZnO. [ABSTRACT FROM AUTHOR]

Processing-In-Memory(PIM) has emerged as a high-performance and energy-efficient computing paradigm for accelerating convolutional neural network (CNN) applications. Resistive random access memory (ReRAM) has been widely used in PIM architectures due to its extremely high efficiency for accelerating matrix-vector multiplications through analog computing. However, because CNN training usually requires high-precision computation in the backward propagation (BP) stage, the limited precision of analog PIM accelerators impedes their adoption in CNN training. In this article, we propose ReHy, a hybrid PIM accelerator to support CNN training in ReRAM arrays. It is composed of Analog PIM (APIM) and Digital PIM (DPIM) modules. ReHy uses APIM to accelerate the feed-forward propagation (FP) stage for high performance, and DPIM to process the BP stage for high accuracy. We exploit the capability of ReRAM for Boolean logic operations to design the DPIM architecture. Particularly, we design floating-point multiplication and addition operators to support matrix multiplications in ReRAM arrays. We also propose a performance model to offload high-precision matrix multiplications to DPIM according to the data parallelism. Experimental results show that ReHy can speed up CNN training by 48.8× and 2.4×, and reduce energy consumption by 35.1× and 2.33×, compared with CPU/GPU architectures (baseline) and the state-of-the-art FloatPIM, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Fuzhou University is the property of Journal of Fuzhou University, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Resistive random‐access memory (ReRAM) has been considered for future memory devices, because of its low‐power consumption and a high degree of integration. In this study, hybrid (H‐) ReRAM devices are proposed using ultra‐thin (<10 nm) Al, Hf, and Zr hybrid films prepared via initiated chemical vapor deposition (iCVD). The hybrid films homogeneously consist of organic and inorganic components, which allow simultaneous metal atoms migration and oxygen vacancy generation. Regardless of hybrid matrix, H‐ReRAMs show highly reliable performance results (on/off ratio >104, endurance >106, retention >104 s), which are notable results compared to conventional ReRAM devices. The resistance changes of the conducting filament in the devices are observed under various temperature conditions to prove the heterogenous filament dynamics in the hybrid matrix. The conducting filament composes of a metallic component and oxygen vacancies give unique properties to H‐ReRAM devices, according to the combination of electrode and hybrid material. It has the potential to precise control of conducting filament by two different filament dynamics in the hybrid matrix. The H‐ReRAM is one of the candidates for alternative memory devices as well as neuromorphic and cognitive computing devices. [ABSTRACT FROM AUTHOR]

Activation energy, bipolar resistance switching behavior, and the electrical conduction transport properties of ITOX:SiO2 thin film resistive random access memory (RRAM) devices were observed and discussed. The ITOX:SiO2 thin films were prepared using a co-sputtering deposition method on the TiN/Si substrate. For the RRAM device structure fabrication, an Al/ITOX:SiO2/TiN/Si structure was prepared by using aluminum for the top electrode and a TiN material for the bottom electrode. In addition, grain growth, defect reduction, and RRAM device performance of the ITOX:SiO2 thin film for the various oxygen gas flow conditions were observed and described. Based on the I-V curve measurements of the RRAM devices, the turn on-off ratio and the bipolar resistance switching properties of the Al/ITOX:SiO2/TiN/Si RRAM devices in the set and reset states were also obtained. At low operating voltages and high resistance values, the conductance mechanism exhibits hopping conduction mechanisms for set states. Moreover, at high operating voltages, the conductance mechanism behaves as an ohmic conduction current mechanism. Finally, the Al/ITOX:SiO2/TiN/Si RRAM devices demonstrated memory window properties, bipolar resistance switching behavior, and nonvolatile characteristics for next-generation nonvolatile memory applications.

Research and development into resistive switching memories, such as resistive random access memory (ReRAM) and memristors, are being actively promoted toward the realization of new computing techniques. To improve the reliability of these devices, it is important to clarify their resistance characteristics. Low‐frequency‐noise spectroscopy (LFNS) is a powerful method for investigating the nature of traps in conduction paths, even at the nanoscale. In this article, the results of LFNS measurements on a TaOx‐based ReRAM device are presented. The temperature dependence of the noise spectra at given frequencies reveals the existence of multiple trap levels, which are observed over a wide range of resistance values. These experimental results show that the ReRAM device is particularly advantageous when used in analog resistive switching applications. [ABSTRACT FROM AUTHOR]

Artificial intelligence algorithms are being adopted to analyze medical data, promising faster interpretation to support doctors' diagnostics. The next frontier is to bring these powerful algorithms to implantable medical devices. Herein, a closed‐loop solution is proposed, where a cellular neural network is used to detect abnormal wavefronts and wavebrakes in cardiac signals recorded in human tissue is trained to achieve >96% accuracy, >92% precision, >99% specificity, and >93% sensitivity, when floating point precision weights are assumed. Unfortunately, the current hardware technologies for floating point precision are too bulky or energy intensive for compact standalone applications in medical implants. Emerging device technologies, such as memristors, can provide the compact and energy‐efficient hardware fabric to support these efforts and can be reliably embedded with existing sensor and actuator platforms in implantable devices. A distributed design that considers the hardware limitations in terms of overhead and limited bit precision is also discussed. The proposed distributed solution can be easily adapted to other medical technologies that require compact and efficient computing, like wearable devices and lab‐on‐chip platforms. [ABSTRACT FROM AUTHOR]

This work explores the phenomenon of HfO2 resistive random access memory (RRAM) postprogramming resistance relaxation using experimental data and kinetic Monte Carlo (KMC) physical simulation. This issue has become an important limitation for multilevel cell (MLC) applications. The physical KMC simulation replicates the RRAM cell‐to‐cell intrinsic resistance variability due to the conductive filament (CF) morphology fluctuations and the weak correlation between the number of oxygen vacancies and the resulting resistance. It furthermore accurately simulates the vacancies' microscopic dynamics within the CF that are responsible for the RRAM resistance relaxation. A link between programming current, CF size/configuration, and relaxation amplitude is clarified and shows the ensuing benefits and limitations of smart programming techniques (read & verify) for MLC applications. Coupled with experimental data obtained on HfO2‐based RRAM arrays, this simulation paves the way to a better understanding of the physics at stake in the RRAM relaxation process and provides guidelines to potential technological solutions for MLC reliability prediction. [ABSTRACT FROM AUTHOR]

Reset-first resistive random access memory (RRAM) devices were demonstrated for off-stoichiometric Ni1−xO thin films deposited using reactive sputtering with a high oxygen partial pressure. The Ni1−xO based RRAM devices exhibited both unipolar and bipolar resistive switching characteristics without an electroforming step. Auger electron spectroscopy showed nickel deficiency in the Ni1−xO films, and X-ray photoemission spectroscopy showed that the Ni3+ valence state in the Ni1−xO films increased with increasing oxygen partial pressure. Conductive atomic force microscopy showed that the conductivity of the Ni1−xO films increased with increasing oxygen partial pressure during deposition, possibly contributing to the reset-first switching of the Ni1−xO films. [ABSTRACT FROM AUTHOR]

This article investigates the spatial tailoring of nitrogen vacancies by atomic layer annealing (ALA) on resistive random access memory (RRAM) devices with an AlN resistive switching layer. The ALA technique involves the in-situ layer-by-layer He/Ar plasma treatment in the cycle of atomic layer deposition for AlN. The AlN RRAM devices prepared with the ALA treatment near the TiN electrode have significantly superior uniformity of the operation voltages and the switching resistances, along with a lower cycle-to-cycle variation in endurance. This enhancement could be attributed to the relatively stable location of rupture and formation of conductive filaments, as a result of the film densification and the suppression of nitrogen vacancies in the AlN region treated with the ALA process. The AlN RRAM devices also demonstrate excellent retention of more than 106 seconds at 125°C. In addition, the ultra-thin 3.3 nm AlN switching layer contributes to low operation voltages of AlN RRAM. The outcomes manifest that the ALA technique could effectively improve the properties of nanoscale materials through precise spatial tailoring, with an accuracy up to atomic scale. [Display omitted] • ALA involves in-situ, layer-by-layer plasma treatment during AlN deposition by ALD. • ALA contributes to film densification and suppression of nitrogen vacancies in AlN. • The uniformity of AlN RRAM properties is improved by ALA near the TiN electrode. • Stable rupture and formation of conductive filaments due to ALA near TiN electrode. • Ultrathin (3.3 nm) AlN in RRAM exhibits low operation voltages and good retention. [ABSTRACT FROM AUTHOR]

Memristor-based deep learning accelerators provide a promising solution to improve the energy efficiency of neuromorphic computing systems. However, the electrical properties and crossbar structure of memristors make these accelerators error-prone. In addition, due to the hardware constraints, the way to deploy neural network models on memristor crossbar arrays affects the computation parallelism and communication overheads. To enable reliable and energy-efficient memristor-based accelerators, a simulation platform is needed to precisely analyze the impact of non-ideal circuit/device properties on the inference accuracy and the influence of different deployment strategies on performance and energy consumption. In this paper, we propose a flexible simulation framework, DL-RSIM, to tackle this challenge. A rich set of reliability impact factors and deployment strategies are explored by DL-RSIM, and it can be incorporated with any deep learning neural networks implemented by TensorFlow. Using several representative convolutional neural networks as case studies, we show that DL-RSIM can guide chip designers to choose a reliability-friendly design option and energy-efficient deployment strategies and develop optimization techniques accordingly. [ABSTRACT FROM AUTHOR]

Considering a high‐density vertical X‐point memory array, the film thickness of an active device for the selector and memory needs to be scaled down. Here, the authors propose an AgTe/HfOx‐based hybrid memory device with a film thickness of less than 10 nm by adopting a bilayer (HfO1.8/HfO2) film using precise composition control. Non‐volatile switching characteristics can be obtained by considering the formation of stable nanoscale Ag filaments in the nanoporous region in non‐stoichiometric HfO1.8 deposited via sputtering. By contrast, volatile switching characteristics are achieved by an unstable atomic‐scale Ag path in stoichiometric HfO2 deposited via plasma‐enhanced atomic layer deposition. Based on density functional theory calculations, it is confirmed that the stoichiometry of the HfOx film is the key parameter that controls the switching characteristics. The bilayer (HfO1.8/HfO2) device exhibits excellent hybrid memory characteristics, such as distinct read margin (>1.5 V), high ON/OFF ratio (>106), and extremely low OFF current (≈pA), for vertical X‐point memory applications. [ABSTRACT FROM AUTHOR]

Interest in resistive random access memory (RRAM) has grown rapidly in recent years for realizing ultrahigh density data storage devices. However, sneak currents in these devices can result in misreading of the data, thus limiting the applicability of RRAM. Complementary resistive switching (CRS) memory consisting of two antiserial RRAMs can considerably reduce sneak currents; however, complicated device architectures and manufacturing processes still remain as challenges. Herein, an effective and simple approach for fabricating CRS memory devices using self‐assembled block copolymer micelles is reported. Cu ions are selectively placed in the core of polystyrene‐block‐poly(2‐vinylpyridine) spherical micelles, and a hexagonally packed micelle monolayer is prepared through spin‐coating. The micelle monolayer can be a symmetrical resistive switching layer, because the micelles and Cu act as dielectric and active metals in memory devices, respectively. The locally enhanced electric field and Joule heating achieved by the structured Cu atoms inside the micelles promote metal ionization and ion migration in a controlled manner, thus allowing for position selectivity during resistive switching. The micelle‐based memory device exhibits stable and reliable CRS behavior, with a nonoverlapping and narrow distribution of threshold voltages. Therefore, this approach is promising for fabricating CRS memory devices for high‐performance and ultrahigh‐density RRAM applications. [ABSTRACT FROM AUTHOR]

Despite the great promises that the resistive random access memory (ReRAM) has shown as the next generation of non-volatile memory technology, its crossbar array structure leads to a severe sneak path interference to the signal read back from the memory cell. In this paper, we first propose a novel belief propagation (BP) based detector for the sneak path interference in ReRAM. Based on the conditions for a sneak path to occur and the dependence of the states of the memory cells that are involved in the sneak path, a Tanner graph for the ReRAM channel is constructed, inside which specific messages are updated iteratively to get a better estimation of the sneak path affected cells. We further combine the graph of the designed BP detector with that of the BP decoder of the polar codes to form a joint detector and decoder. Tailored for the joint detector and decoder over the ReRAM channel, effective polar codes are constructed using the genetic algorithm. Simulation results show that the BP detector can effectively detect the cells affected by the sneak path, and the proposed polar codes and the joint detector and decoder can significantly improve the error rate performance of ReRAM. [ABSTRACT FROM AUTHOR]