Neuromorphic Systems Research Articles

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.

Reset transition in HfO2-Based memristors using a constant power signal

Memristors, also known as resistive switching devices, have great potential for applications in memory and neuromorphic systems. Understanding the switching mechanisms is crucial since ReRAM memories need to operate at high frequencies. It is known the reset transition is dominated by the conductive filament Joule heating. We have studied the reset transition in TiN/Ti/HfO2/W metal–insulator–metal memristors by applying constant power signals to different initial filament thicknesses, which were obtained using different initial low resistance states. The results show that power value controls the reset times, decreasing when the power is increased. On the other hand, larger resistances lead to faster reset transitions. These measurements have allowed us to obtain a value of the thermal resistance of the conductive filament. Moreover, we have observed the reset times as a function of the initial resistance and the power lies on a common plane, which allows us to estimate the transition time by fixing an initial resistance and a power value.

Solving Max-Cut Problem Using Spiking Boltzmann Machine Based on Neuromorphic Hardware with Phase Change Memory.

Efficiently solving combinatorial optimization problems (COPs) such as Max-Cut is challenging because the resources required increase exponentially with the problem size. This study proposes a hardware-friendly method for solving the Max-Cut problem by implementing a spiking neural network (SNN)-based Boltzmann machine (BM) in neuromorphic hardware systems. To implement the hardware-oriented version of the spiking Boltzmann machine (sBM), the stochastic dynamics of leaky integrate-and-fire (LIF) neurons with random walk noise are analyzed, and an innovative algorithm based on overlapping time windows is proposed. The simulation results demonstrate the effective convergence and high accuracy of the proposed method for large-scale Max-Cut problems. The proposed method is validated through successful hardware implementation on a 6-transistor/2-resistor (6T2R) neuromorphic chip with phase change memory (PCM) synapses. In addition, as an expansion of the algorithm, several annealing techniques and bias split methods are proposed to improve convergence, along with circuit design ideas for efficient evaluation of sampling convergence using cell arrays and spiking systems. Overall, the results of the proposed methods demonstrate the potential of energy-efficient and hardware-implementable approaches using SNNs to solve COPs. To the best of the author's knowledge, this is the first study to solve the Max-Cut problem using an SNN neuromorphic hardware chip.

Wrinkled Rhenium Disulfide for Anisotropic Nonvolatile Memory and Multiple Artificial Neuromorphic Synapses.

Two-dimensional materials are emerging as potential solutions for high-density nonvolatile memory and efficient neuromorphic computing. However, integrating multidimensional memory and an ideal linear weight updating synapse in a simple device configuration to achieve versatile biomimetic neuromorphic systems remains challenging. Here, we introduce a wrinkled rhenium disulfide (ReS2) transistor, where the wrinkled structure facilitates the carrier trapping/detrapping at the dielectric interface, thus enabling the fusion of nonvolatile memory and both electronic and optoelectronic synaptic functionalities. As a nonvolatile memory, anisotropic wrinkled ReS2 can yield three distinct sets of data across three crystal orientations under identical programming operations. Each set demonstrates exceptional retention and endurance properties. As a neuromorphic synapse, it realizes the linear and symmetric updates of conductance states up to 9 bits and 8 bits, the ultra-low-energy consumption of 75 fJ and 2.5 pJ under the electrical and optical stimuli, respectively. The artificial neural network (ANN) based on electronic synapses gives a superior recognition accuracy of 92.9% for the original handwritten digits. The anisotropic synaptic responses and multiwavelength sensitivities of optoelectronic synapses enable them to execute advanced memory and recognition functions for complex images that encompass a variety of pattern features or color information. This underscores its substantial potential for integration into efficient biomimetic visual systems.

Spike-based rotation detection using a self-powered triboelectric sensor with mimicry of a vestibular system

The biological vestibular system in semicircular canals detects head rotation with high energy efficiency through its unique spike-based processing. We propose a self-powered vestibular sensory neuron inspired by the biological vestibular system and utilizing a triboelectric nanogenerator (TENG) as a rotation sensor and a neuron transistor (neuristor) as a spiking neuron. This artificial vestibular neuron simultaneously detects the angular velocity and encodes it into spikes. When the angular velocity that is applied to the TENG increases, the spiking frequency increases, and this is a desired property of the vestibular neuron. Therefore, the vestibular neuron can serve as an input neuron in a spiking neural network (SNN). We also demonstrate a fully hardware-based neuromorphic system that is attractive for its improved energy efficiency to recognize rotation axes. Compared to a vestibular system based on conventional von-Neumann computing, that based on the proposed neuromorphic computing can effectively reduce power consumption by adopting spike transmission and employing the self-powered sensor. The proposed system is promising for applications related to rotation that demands high energy-efficiency.

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.

Stochastic Memristor Modeling Framework Based on Physics-Informed Neural Networks

In this paper, we present a framework of modeling memristor noise for circuit simulators using physics-informed neural networks (PINNs). The variability of the memristor that is directly related to the neuromorphic system can be handled with this approach. The memristor noise model is transformed into a Fokker–Planck equation (FPE) from a probabilistic perspective. The translated equations are physically interpreted through the PINN. The weights and biases extracted from the PINN are implemented in Verilog-A through simple operations. The characteristics of the stochastic system under the noise are obtained by integrating the probability density function. This approach allows for the unification of different memristor models and the analysis of the effects of noise.

A Flexible Artificial Spiking Photoreceptor Enabled by a Single VO2 Mott Memristor for the Spike-Based Electronic Retina.

The neuromorphic vision system that utilizes spikes as information carriers is crucial for the formation of spiking neural networks. Here, we present a bioinspired flexible artificial spiking photoreceptor (ASP), which is realized by using a single VO2 Mott memristor that can simultaneously sense and encode the stimulus light into spikes. The ASP has high spike-encoded photosensitivity and ultrawide photosensing range (405-808 nm) with good endurance (>7 × 107) and high flexibility (bending radius ∼5 mm). Then, we put forward an all-spike electronic retina architecture that comprises one layer of ASPs and one layer of artificial optical nerves (AONs) to process the spike information. Each AON consists of a single Mott memristor connected in series with a neuro-transistor that is a multiple-input floating-gate MOS transistor. Simulation results demonstrate that the all-spike electronic retina can successfully segment images with high Shannon entropy, thus laying the foundation for the development of a spike-based neuromorphic vision system.

Inhibiting the current spikes within the channel layer of LiCoO2-based three-terminal synaptic transistors

Synaptic transistors, which emulate the behavior of biological synapses, play a vital role in information processing and storage in neuromorphic systems. However, the occurrence of excessive current spikes during the updating of synaptic weight poses challenges to the stability, accuracy, and power consumption of synaptic transistors. In this work, we experimentally investigate the main factors for the generation of current spikes in the three-terminal synaptic transistors that use LiCoO2 (LCO), a mixed ionic-electronic conductor, as the channel layer. Kelvin probe force microscopy and impedance testing results reveal that ion migration and adsorption at the drain–source-channel interface cause the current spikes that compromise the device's performance. By controlling the crystal orientation of the LCO channel layer to impede the in-plane migration of lithium ions, we show that the LCO channel layer with the (104) preferred orientation can effectively suppress both the peak current and power consumption in the synaptic transistors. Our study provides a unique insight into controlling the crystallographic orientation for the design of high-speed, high-robustness, and low-power consumption nano-memristor devices.

Chiral Perovskite Nanowire Optoelectronic Synapse for Full‐Stokes Polarization‐Resolved Perception and Reservoir Computing

AbstractFull‐Stokes polarization‐resolved photonic artificial synapse (PAS) devices with in‐sensor computing capabilities show great potential for multimode vision perception and processing. However, current polarization‐resolved PAS devices are limited to monotonic recognition of linearly polarized light or circularly polarized light. Here, the study develops a chiral perovskite nanowire‐based PAS device as a full‐Stokes polarimeter to achieve polarization‐dependent neuromorphic optoelectronics. The device demonstrates a significantly high circular dichroism of over 400 millidegree and intrinsic linear dichroism, contributing to effectively sensing polarized light. Efficient charge separation at the perovskite NW/MXene heterostructure results in a prolonged carrier lifetime, thereby achieving a high responsivity of 2.3 AW−1, excellent synaptic behavior, and low power consumption of 0.5 pJ per synaptic stimuli. Significantly, the polarization‐modulated reservoir computing is developed based on the full‐Stokes PAS device, which exhibits a low normalized root mean square error of 0.023 in the chaotic system forecasting task. The single‐nanowire PAS device with the capability of sensing full‐Stokes parameters demonstrates great significance in building advanced energy‐efficient polarization‐resolved nanoscale neuromorphic vision systems.

Synaptic Feature of Quantum Dot Light-Emitting Diodes for Visualization of Learning Process.

Brain-inspired electronics with synaptic functions hold significant promise for advancing artificial intelligent applications. In this study, we demonstrate the synaptic feature of quantum-dot light-emitting diodes (QLEDs), which can convert electrical pulses into synapse-like light signals (the brightness gradually increases as the electrical pulses are prolonged). These features are analogous to learning and forgetting in biological synapses. The enhancement of brightness can be attributed to the reduction of charge transfer from the quantum dots to ZnO electron transport layer and resistive switching effect. With an integrated complementary metal-oxide-semiconductor (CMOS) drive, arrayed synaptic QLEDs can simulate the visualization of brain-like learning processes, which can reduce the noise toward high image recognition rate (>95.0%) by deep neural networks. Our findings introduce a novel brain-inspired optoelectronic approach with potential applications in optical neuromorphic systems.

Color Recognition Achieved in Multiwavelength Controlled Plasmonic Optoelectronic Memristor for Neuromorphic Visual System

AbstractAn optoelectronic synaptic device with the color‐recognition ability is highly desired for achieving the high‐efficient neuromorphic color visual system. In order to realistically implement the functionality of retina (i.e., bipolar cells and cones photoreceptors), the exploration of multiwavelength controlled optoelectronic synaptic devices with fully light tunable ability would be sorely needed. Here, a multiwavelength controlled plasmonic optoelectronic memristor based on the size‐dependent localized surface plasmon resonance (LSPR) of metallic nanostructures is developed. The distinguishable red (R), green (G), and blue (B) light response behaviors can be achieved in this single device, which enables the realization of color image perception and memory functions. The RGB light‐strengthened synaptic plasticity can be depressed by ultraviolet light stimulations, relying on the effects of LSPR and optical excitation in WOx:Ag nanocomposites. Moreover, the visual attention for color (color discrimination) is realized in this memristor, which promotes the improvement of recognition accuracy during the color image recognition process. A new approach in developing multiwavelength controlled synaptic devices is provided here for highly efficient neuromorphic vision.

Monolithically integrated neuromorphic electronic skin for biomimetic radiation shielding.

Melanogenesis, a natural responsive mechanism of human skin to harmful radiation, is a self-triggered defensive neural activity safeguarding the body from radiation exposure in advance. With the increasing significance of radiation shielding in diverse medical health care and wearable applications, a biomimetic neuromorphic optoelectronic system with adaptive radiation shielding capability is often needed. Here, we demonstrate a transparent and flexible metal oxide-based photovoltaic neuromorphic defensive system. By using a monolithically integrated ultraflexible optoelectronic circuitry and electrochromic device, seamless neural processing for ultraviolet (UV) radiation shielding including history-based sensing, memorizing, risk recognition, and blocking can be realized with piling the entire signal chain into the flexible devices. The UV shielding capability of the system can be evaluated as autonomous blocking up to 97% of UV radiation from 5 to 90 watts per square meter in less than 16.9 seconds, demonstrating autonomously modulated sensitivity and response time corresponding to UV environmental conditions and supplied bias.

The Effects of Omeprazole on the Neuron-like Spiking of the Electrical Potential of Proteinoid Microspheres.

This study examines a new approach to hybrid neuromorphic devices by studying the impact of omeprazole-proteinoid complexes on Izhikevich neuron models. We investigate the influence of these metabolic structures on five specific patterns of neuronal firing: accommodation, chattering, triggered spiking, phasic spiking, and tonic spiking. By combining omeprazole, a proton pump inhibitor, with proteinoids, we create a unique substrate that interfaces with neuromorphic models. The Izhikevich neuron model is used because it is computationally efficient and can accurately simulate the various behaviours of cortical neurons. The results of our simulations show that omeprazole-proteinoid complexes have the ability to affect neuronal dynamics in different ways. This suggests that they could be used as adjustable components in bio-inspired computer systems. We noticed a notable alteration in the frequency of spikes, patterns of bursts, and rates of adaptation, especially in chattering and triggered spiking behaviours. The findings indicate that omeprazole-proteinoid complexes have the potential to serve as adaptable elements in neuromorphic systems, presenting novel opportunities for information processing and computation that have origins in neurobiological principles. This study makes a valuable contribution to the expanding field of biochemical neuromorphic devices and establishes a basis for the development of hybrid bio-synthetic computational systems.

Recent trends in neuromorphic systems for non-von Neumann in materia computing and cognitive functionalities

In the era of artificial intelligence and smart automated systems, the quest for efficient data processing has driven exploration into neuromorphic systems, aiming to replicate brain functionality and complex cognitive actions. This review assesses, based on recent literature, the challenges and progress in developing basic neuromorphic systems, focusing on “material-neuron” concepts, that integrate structural similarities, analog memory, retention, and Hebbian learning of the brain, contrasting with conventional von Neumann architecture and spiking circuits. We categorize these devices into filamentary and non-filamentary types, highlighting their ability to mimic synaptic plasticity through external stimuli manipulation. Additionally, we emphasize the importance of heterogeneous neural content to support conductance linearity, plasticity, and volatility, enabling effective processing and storage of various types of information. Our comprehensive approach categorizes fundamentally different devices under a generalized pattern dictated by the driving parameters, namely, the pulse number, amplitude, duration, interval, as well as the current compliance employed to contain the conducting pathways. We also discuss the importance of hybridization protocols in fabricating neuromorphic systems making use of existing complementary metal oxide semiconductor technologies being practiced in the silicon foundries, which perhaps ensures a smooth translation and user interfacing of these new generation devices. The review concludes by outlining insights into developing cognitive systems, current challenges, and future directions in realizing deployable neuromorphic systems in the field of artificial intelligence.

Reliable resistive switching and synaptic simulation behaviors in ammonium polyphosphate-based memristor with non-inert Al electrode

Abstract Memristive devices that integrate storage and computing capabilities are highly promising candidates for artificial synapses in neuromorphic systems. However, achieving both cost-effectiveness and high-performance in memristors remains a substantial challenge. Ammonium polyphosphate (APP), an all-inorganic ionic polymer, has been utilized in the fabrication of memristive devices due to its distinctive poly-ionic properties and exceptional ion mobility. In this study, a two-terminal APP-based memristor with an Al/APP/ITO structure was fabricated. The experimental results revealed improved bipolar resistive switching behavior, characterized by lower operating voltages, enhanced endurance performance, and extended retention time. Detailed data fitting and chemical bonding analysis suggest that the physical mechanism underlying resistive switching involves a combination of interfacial Schottky barrier and conductive filaments. Furthermore, adjustable device conductance is achieved by applying consecutive positive and negative voltage sweeps. Various synaptic functions, including excitatory postsynaptic current, short-term paired-pulse facilitation, long-term potentiation /depression, and spike-timing-dependent plasticity, are effectively emulated. This study presents an effective approach to enhancing the memristive characteristics of APP-based devices and positions APP as a viable candidate for innovative neuromorphic architectures.

Simulation-based effective comparative analysis of neuron circuits for neuromorphic computation systems

The spiking neural networks (SNN) which are inspired by the human brain offers wider scope for application in the growth of neuromorphic computing systems due to their brain level computational capabilities, reduced power consumption, minimal data movement cost, and among other advantages. Spike-based neurons and synapses are the essential building blocks of SNN, and their efficient implementation is vital to its performance enhancement. In this regard, the design and implementation of spiking neurons have been the major focus among the researchers. In this paper, functioning of different leaky integrate fire (LIF)-based spiking neuron circuits like frequency adaptable CMOS-based LIF, resistor-capacitor-based (RC) LIF, and volatile memristor-based LIF are subjected to comparison. The work mainly focuses on revealing analysis of spike duration and amplitude, number of spikes produced during excitation period, threshold operation, field of application, and various other significant parameters of aforementioned neuron circuits. Extensive simulations of these circuits are carried out utilizing the Cadence Virtuoso simulation environment in order to validate their behavior. Further, a brief comparative analysis is executed considering into account the attributes like circuit complexity, supply voltage, firing rate, membrane capacitance, nature of input/output, refractory mechanism, and energy consumption per spike. This work seeks to assist researchers in selecting an appropriate LIF model to efficiently construct memristors and/or non-memristors based SNN for certain application.

Photonic Neuromorphic Processing with On‐Chip Electrically‐Driven Microring Spiking Neuron

AbstractGuided by brain‐like temporal processing and event‐driven manner, neuromorphic computing has emerged as a competitive paradigm to realize artificial intelligence with high energy efficiency. Silicon photonics offers an ideal hardware platform with mutual foundry fabrication process and well‐developed device libraries, however, its huge potential to build integrated neuromorphic systems is significantly hindered due to the lack of scalable on‐chip photonic spiking neurons. Here, the first integrated electrically‐driven spiking neuron based on a silicon microring under the carrier injection working mode is reported, which is capable of emulating fundamental neural dynamics including excitability threshold, temporal integration, refractory period, controllable spike inhibition, and precise time encoding at a speed of 250 MHz. By programming time‐multiplexed spike representations, photonic spiking convolution is experimentally realized for image edge feature detection. Besides, a spiking convolutional neural network is constructed by combining photonic convolutional layers with a software‐implemented fully‐connected layer, which yields a classification accuracy of 94.1% on the benchmark Modified National Institute of Standards and Technology database. Moreover, it is theoretically verified that it's promising to further improve the operation speed to a gigahertz level by developing an electro‐optical co‐simulation model. The proposed microring neuron constitutes the final building block of scalable spike activation, thus representing a great breakthrough to boost the development of on‐chip neuromorphic information processing.

Analog Sequential Hippocampal Memory Model for Trajectory Learning and Recalling: A Robustness Analysis Overview

The rapid expansion of information systems in all areas of society demands more powerful, efficient, and low‐energy consumption computing systems. Neuromorphic engineering has emerged as a solution that attempts to mimic the brain to incorporate its capabilities to solve complex problems in a computationally and energy‐efficient way in real time. Within neuromorphic computing, building systems to efficiently store the information is still a challenge. Among all the brain regions, the hippocampus stands out as a short‐term memory capable of learning and recalling large amounts of information quickly and efficiently. Herein, a spike‐based bio‐inspired hippocampus sequential memory model is proposed that makes use of the benefits of analog computing and spiking neural networks (SNNs): noise robustness, improved real‐time operation, and energy efficiency. This model is applied to robotic navigation to learn and recall trajectories that lead to a goal position within a known grid environment. The model is implemented on the special‐purpose SNNs mixed‐signal DYNAP‐SE hardware platform. Through extensive experimentation together with an extensive analysis of the model's behavior in the presence of external noise sources, its correct functioning is demonstrated, proving the robustness and consistency of the proposed neuromorphic sequential memory system.

A Self-Driven Ga2O3 Memristor Synapse for Humanoid Robot Learning.

In recent years, the rapid development of brain-inspired neuromorphic systems has created an imperative demand for artificial photonic synapses that operate with low power consumption. In this study, a self-driven memristor synapse based on gallium oxide (Ga2O3) nanowires is proposed and demonstrated successfully. This memristor synapse is capable of emulating a range of functionalities of biological synapses when exposed to 255nm light stimulation. These functionalities encompass peak time-dependent plasticity, pulse facilitation, and memory learning capabilities. It exhibits an ultrahigh paired-pulse facilitation index of 158, indicating exceptional learning performance. The transition from short-term memory to long-term memory can be attributed to the remarkable relearning capabilities. Furthermore, the potential applications of the memristor synapse is showcased through the successful manipulation of a humanoid intelligent robot. Upon establishing artificial intelligence (AI) systems, the control commands originating from the synaptic device can drive the humanoid robot to perform various actions. Based on the memristor synapses, the autonomous feedback system of the humanoid robot facilitates a good collaboration between robotic actions and bio-inspired light perception. Therefore, this research opens up an effective way to advance the development of neuromorphic computing technologies, AI systems, and intelligent robots that demand ultra-low energy consumption.