Neuromorphic Computing System Research Articles

Temperature effect on a weighted vortex spin-torque nano-oscillator for neuromorphic computing

In this work, we present fabricated magnetic tunnel junctions (MTJs) that can serve as magnetic memories (MMs) or vortex spin-torque nano-oscillators (STNOs) depending on the device geometry. We explore the heating effect on the devices to study how the performance of a neuromorphic computing system (NCS) consisting of MMs and STNOs can be enhanced by temperature. We further applied a neural network for waveform classification applications. The resistance of MMs represents the synaptic weights of the NCS, while temperature acts as an extra degree of freedom in changing the weights and TMR, as their anti-parallel resistance is temperature sensitive, and parallel resistance is temperature independent. Given the advantage of using heat for such a network, we envision using a vertical-cavity surface-emitting laser (VCSEL) to selectively heat MMs and/or STNO when needed. We found that when heating MMs only, STNO only, or both MMs and STNO, from 25 to 75 °C, the output power of the STNO increases by 24.7%, 72%, and 92.3%, respectively. Our study shows that temperature can be used to improve the output power of neural networks, and we intend to pave the way for future implementation of a low-area and high-speed VCSEL-assisted spintronic NCS.

Weight‐Reconfigurable Neuromorphic Computing Systems for Analog Signal Integration

AbstractOwing to the necessity of high computation amounts has emerged, interest in a neuromorphic computing system has significantly increased as a compelling alternative to conventional CMOS technology. This paper presents a neuromorphic hardware algorithm to finely reconfigure multi‐input signal processing, which can be implemented as an advanced processor for diverse external information, and the hydrogen explosion risk assessment system is demonstrated as a proof of concept. Hydrogen concentration and temperature are used as sensory inputs for the signal integration and the precise values of them are determined by offsetting the effect of temperature on the electrical signal from the hydrogen sensor through a sensor circuit. Each signal is then updated by the weight control circuit and converted into a postsynaptic current to represent the hydrogen explosion risk using a multi‐input artificial synapse. This simplicity of the circuitry renders the fabrication of all components and circuits compatible with simple inkjet printing methods, enabling cost‐effective and high‐throughput manufacturing. Additionally, the real‐time demonstration of the neuromorphic computing system is successfully conducted, offering insights into the practical application of neuromorphic computing.

Reconfigurable Ag/HfO2/NiO/Pt Memristors with Stable Synchronous Synaptic and Neuronal Functions for Renewable Homogeneous Neuromorphic Computing System.

Artificial synapses and bionic neurons offer great potential in highly efficient computing paradigms. However, complex requirements for specific electronic devices in neuromorphic computing have made memristors face the challenge of process simplification and universality. Herein, reconfigurable Ag/HfO2/NiO/Pt memristors are designed for feasible switching between volatile and nonvolatile modes by compliance current controlled Ag filaments, which enables stable and reconfigurable synaptic and neuronal functions. A neuromorphic computing system effectively replicates the biological synaptic weight alteration and continuously accomplishes excitation and reset of artificial neurons, which consist of bionic synapses and artificial neurons based on isotype Ag/HfO2/NiO/Pt memristors. This reconfigurable electrical performance of the Ag/HfO2/NiO/Pt memristors takes advantage of simplified hardware design and delivers integrated circuits with high density, which exhibits great potency for future neural networks.

Enhanced read resolution in reconfigurable memristive synapses for Spiking Neural Networks

The synapse is a key element circuit in any memristor-based neuromorphic computing system. A memristor is a two-terminal analog memory device. Memristive synapses suffer from various challenges including high voltage, SET or RESET failure, and READ margin issues that can degrade the distinguishability of stored weights. Enhancing READ resolution is very important to improving the reliability of memristive synapses. Usually, the READ resolution is very small for a memristive synapse with a 4-bit data precision. This work considers a step-by-step analysis to enhance the READ current resolution or the read current difference between two resistance levels for a current-controlled memristor-based synapse. An empirical model is used to characterize the HfO2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\\hbox {HfO}}_{2}$$\\end{document} based memristive device. 1st\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1\ extrm{st}$$\\end{document} and 2nd\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2\ extrm{nd}$$\\end{document} stage device of our proposed synapse design can be scaled to enhance the READ current margin up to ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document} 4.3×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} and ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document} 21%, respectively. Moreover, READ current resolution can be enhanced with run-time adaptation techniques such as READ voltage scaling and body biasing. The READ voltage scaling and body biasing can improve the READ current resolution by about 46% and 15%, respectively. TENNLab’s neuromorphic computing framework is leveraged to evaluate the effect of READ current resolution on classification, control, and reservoir computing applications. Higher READ current resolution shows better accuracy than lower resolution even when facing different levels of read noise.

SiC@NiO Core-Shell Nanowire Networks-Based Optoelectronic Synapses for Neuromorphic Computing and Visual Systems at High Temperature.

1D nanowire networks, sharing similarities of structure, information transfer, and computation with biological neural networks, have emerged as a promising platform for neuromorphic systems. Based on brain-like structures of 1D nanowire networks, neuromorphic synaptic devices can overcome the von Neumann bottleneck, achieving intelligent high-efficient sensing and computing function with high information processing rates and low power consumption. Here, high-temperature neuromorphic synaptic devices based on SiC@NiO core-shell nanowire networks optoelectronic memristors (NNOMs) are developed. Experimental results demonstrate that NNOMs attain synaptic short/long-term plasticity and modulation plasticity under both electrical and optical stimulation, and exhibit advanced functions such as short/long-term memory and "learning-forgetting-relearning" under optical stimulation at both room temperature and 200°C. Based on the advanced functions under light stimulus, the constructed 5×3 optoelectronic synaptic array devices exhibit a stable visual memory function up to 200°C, which can be utilized to develop artificial visual systems. Additionally, when exposed to multiple electronic or optical stimuli, the NNOMs effectively replicate the principles of Pavlovian classical conditioning, achieving visual heterologous synaptic functionality and refining neural networks. Overall, with abundant synaptic characteristics and high-temperature thermal stability, these neuromorphic synaptic devices offer a promising route for advancing neuromorphic computing and visual systems.

A nanosecond-scale CuI synaptic memristor prepared by a solution-based process

Owing to the synaptic behaviors and functions, memristors are intensively studied as a critical component for the neuromorphic computing system which is considered as an effective scenario to tackle the performance bottleneck existing in modern computers based on the von Neumann architecture. A novel synaptic device base on the CuI memristor prepared with a solution-based process is proposed in this work, and a set of synaptic features are emulated. The electrochemical metallization contributes to the resistive switching behavior and small operating voltages (Vset = 0.67 V and Vreset = −0.33 V). Moreover, the CuI memristor exhibits the small switching energy (23 pJ) and ultraquick switching speed (100 ns). A large CuI memristor array is realized experimentally, by which the hardware-based multiply-and-accumulate (MAC) operation is implemented. Furthermore, the hardware-based convolution computation in image processing is realized based on the MAC operation, demonstrating the potential applications in image processing requiring the high degree of parallelism.

High‐Entropy Perovskite Oxide Photonic Synapses

AbstractHigh‐entropy oxides are garnering increased attention due to their unique properties engineered by chemical disorders. Chemical disorders can cause random potential spatial fluctuations and the resulting anomalous photoconductivity, while they have not yet been exploited in high‐entropy oxides for usefulness. In this work, persistent photoconductivity (PPC) behavior in high‐entropy perovskite Ba(Zr0.2Sn0.2Ti0.2Hf0.2Nb0.2)O3 thin films is reported and used it as a basis to develop artificial photonic synapses. This photonic synapse can emulate distinctive biological synaptic features such as excitatory postsynaptic current, paired‐pulse facilitation, transition from short‐term memory to long‐term memory, and learning‐forgetting processes. This photonic synapse can also implement the basic “AND” and “OR” logic operations. In addition, a 5×5 photonic synaptic array is built to mimic the spatiotemporal sensing and memory functions of a visual sensing‐memory system, exhibiting the improved accuracy of dynamic machine vision classification tasks as compared to traditional visual sensing systems. This study highlights the potential of high‐entropy oxides for application in neuromorphic computing and dynamic machine vision systems.

ICNCS: Internal Cascaded Neuromorphic Computing System for Fast Electric Vehicle State-of-Charge Estimation

Accuracy and speed of Lithium-ion battery state of charge (SOC) estimation determine the reliability and stability of electric vehicle (EV), as well as promoting the development of smart home energy management system. Existing SOC estimation approaches embedded in commercial EVs still suffer from limitations of low precision, effectiveness, and relatively low robustness. To address these issues, we propose an internal cascaded neuromorphic computing system (ICNCS) via memristor circuits for EV SOC estimation. Specifically, we use three circuit modules to facilitate the design of the proposed ICNCS. Firstly, a bidirectional gated recurrent unit (Bi-GRU) circuit module is designed, enabling adequate feature extraction from the time-contextual battery information. Secondly, an attention circuit module is proposed to distinguish the useful and unimportant information related to SOC estimation. Thirdly, the Kalman filter module is constructed to eliminate the random noise caused by data transmission and processing. Finally, a series of experiments and analysis demonstrate that the proposed ICNCS has good performances in terms of accuracy (the lowest achievable RMSE and MAE are 0.853 and 0.711, respectively), time efficiency (approximately 16 20 times), and robustness (anti-noise capacity), indicating an advancement in consumer electronics applications.

Current-Controllable and Reversible Multi-Resistance-State Based on Domain Wall Number Transition in 2D Ferromagnet Fe3GeTe2.

Controlling the multi-state switching is significantly essential for the extensive utilization of 2D ferromagnet in magnetic racetrack memories, topological devices, and neuromorphic computing devices. The development of all-electric functional nanodevices with multi-state switching and a rapid reset remains challenging. Herein, to imitate the potentiation and depression process of biological synapses, a full-current strategy is unprecedently established by the controllable resistance-state switching originating from the spin configuration rearrangement by domain wall number modulation in Fe3GeTe2. In particular, a strong correlation is uncovered in the reduction of domain wall number with the corresponding resistance decreasing by in-situ Lorentz transmission electron microscopy. Interestingly, the magnetic state is reversed instantly to the multi-domain wall state under a single pulse current with a higher amplitude, attributed to the rapid thermal demagnetization by simulation. Based on the neuromorphic computing system with full-current-driven artificial Fe3GeTe2 synapses with multi-state switching, a high accuracy of ≈91% is achieved in the handwriting image recognition pattern. The results identify 2D ferromagnet as an intriguing candidate for future advanced neuromorphic spintronics.

Reconfigurable multifunctional neuromorphic memristor fabricated from two-dimensional ReSe2 ferroelectric nanosheet films

Memristor-based neuromorphic computing is beneficial for artificial intelligence to process external information autonomously with high speed and high efficiency. Two-dimensional (2D) layered van der Waals rhenium selenide (ReSe2) has optoelectronic and semiconductor properties, but its ferroelectricity has not been confirmed fully experimentally and the application exploration is currently limited. Here, we experimentally confirmed the room-temperature ferroelectricity of 2D ReSe2 and proposed a reconfigurable ReSe2 memristor that can realize multiple functions. The device can realize the conductance bidirectional regulation, and under the action of electrical signals, it exhibits the high 0.99 and 0.98 linearity and accurate bidirectional update of weights. Under the complementary effect of ReSe2 ferroelectric polarization flipping and interface defects, the device exhibits the memcapacitor and memristor reconfigurable behavior and multiple functions such as visible light perception, logical “OR” calculation, and long/short-term synaptic plasticity. In addition, the six-layer convolutional neural network built based on ReSe2 memristors can perform feature extraction and classification recognition of handwritten digital pictures, and its recognition accuracy can reach 97.04%. In addition to obtain substantial experimental evidence for the ferroelectricity of 2D ReSe2, this work also provides a new avenue for the implementation of ReSe2 ferroelectric memristors in the neuromorphic computing system with the front-end sensing and back-end processing.

Adapted MLP-Mixer network based on crossbar arrays of fast and multilevel switching (Co-Fe-B)x(LiNbO3)100-x nanocomposite memristors.

MLP-Mixer based on multilayer perceptrons (MLPs) is a novel architecture of a neuromorphic computing system (NCS) introduced for image classification tasks without convolutional layers. Its software realization demonstrates high classification accuracy, although the number of trainable weights is relatively low. One more promising way of improving the NCS performance, especially in terms of power consumption, is its hardware realization using memristors. Therefore, in this work, we proposed an NCS with an adapted MLP-Mixer architecture and memristive weights. For this purpose, we used a passive crossbar array of (Co-Fe-B)x(LiNbO3)100-x memristors. Firstly, we studied the characteristics of such memristors, including their minimal resistive switching time, which was extrapolated to be in the picosecond range. Secondly, we created a fully hardware NCS with memristive weights that are capable of classification of simple 4-bit vectors. The system was shown to be robust to noise introduction in the input patterns. Finally, we used experimental memristive characteristics to simulate an adapted MLP-Mixer architecture that demonstrated a classification accuracy of (94.7 ± 0.3)% on the Modified National Institute of Standards and Technology (MNIST) dataset. The obtained results are the first steps toward the realization of memristive NCS with a promising MLP-Mixer architecture.

MLG-NCS: Multimodal Local–Global Neuromorphic Computing System for Affective Video Content Analysis

MLG-NCS: Multimodal Local–Global Neuromorphic Computing System for Affective Video Content Analysis

Principles of analog neuromorphic computing: from components to systems and algorithms

This report presents the current state of affairs in the implementation of artificial intelligence hardware accelerators based on practically successful neural network algorithms of the first and second generations based on formal artificial neural networks (ANNs). The shortcomings of existing solutions are noted and ways to overcome them using analog neuromorphic architectures are outlined. The latter are created on the principles of the structuring and functioning of a living nervous system, using artificial neurons and models of synaptic contacts - the so–called memristors, electrically rewritable nanoscale elements of non-volatile memory [1-3]. With the use of these elements, it is possible to significantly increase the performance and energy efficiency of algorithm accelerators based on the ANNs [4-6], as well as the formation of promising computing systems based on bioplausible 3rd generation neural network algorithms - Spiking Neural Networks (SNNs) [7-9]. The original method of substantiating the optimal rules for local tuning SNNs with frequency encoding and the possibility of their implementation in the form of the Spike-Timing-Dependent Plasicity (STDP) are discussed [10]. The results of SNN learning stability to a variability of analog memristors, as well as the use of noise as a constructive factor in the fine-tuning and maintenance of SNN memristive weights are demonstrated [7, 11]. Also, approaches to the implementation of local plasticity rules with dopamine-like modulation as a type of SNN reinforcement learning are discussed. The latter is necessary for the formation of imitative "needs" of an agent in the process of its autonomous functioning [12, 13, 14]. The first results on the creation of a prototype of a memristive implantable neuroprosthesis of the motor activity are considered [15, 16]. Finally, possible hardware solutions for both neuronal elements and synaptic connections based on suitable memristive devices are demonstrated. The concept and first results on the creation of an analog neuromorphic computing system based on the above components are presented. Thus, an attempt is made to systematize the existing and original methods of implementing energy-efficient and compact analog neuromorphic computing systems for real-time and life-learning artificial intelligence.

Perovskite-based optoelectronic systems for neuromorphic computing

Brain-like neuromorphic computing system offers the ability to be used in neural networks on demand and are rapidly gaining interest by researchers due to their outstanding photoelectric stimulation response-ability and multi-segment storage function. In this work, we show the processing capabilities of the neuromorphic computing units for optoelectronic signals and high label noise ratio signals. Demonstrated the functions of potassium ion doped perovskite-based unit resembles properties found in neuronal synapses. Potassium ion passivates perovskite and promotes the formation of the electric double layer and ion doping in the unit so that the unit can simulate the characteristics of biological synapses generated by various electrical simulations according to the demand. Perovskite significantly enhances the unit's responsiveness to light pulses in the visible light range. By implementing the 'resolving training biases via influence-base data relabeling' strategy, the unit demonstrates remarkable performance in high noise recognition tasks. These results open a new direction for the construction of brain-like computers that deal with a complex and high proportion of harmful samples.

AD 2 VNCS: A dversarial D efense and D evice V ariation-tolerance in Memristive Crossbar-based N euromorphic C omputing S ystems

In recent years, memristive crossbar-based neuromorphic computing systems (NCS) have obtained extremely high performance in neural network acceleration. However, adversarial attacks and conductance variations of memristors bring reliability challenges to NCS design. First, adversarial attacks can fool the neural network and pose a serious threat to security critical applications. However, device variations lead to degradation of the network accuracy. In this article, we propose DFS (Deep neural network Feature importance Sampling) and BFS (Bayesian neural network Feature importance Sampling) training strategies, which consist of Bayesian Neural Network (BNN) prior setting, clustering-based loss function, and feature importance sampling techniques, to simultaneously combat device variation, white-box attack, and black-box attack challenges. Experimental results clearly demonstrate that the proposed training framework can improve the NCS reliability.

Artificial Visual Synaptic Architecture with High-Linearity Light-Modulated Weight for Optoelectronic Neuromorphic Computing.

A brain-like neuromorphic computing system, as compared with traditional Von Neumann architecture, has broad application prospects in the fields of emerging artificial intelligence (AI) due to its high fault tolerance, excellent plasticity, and parallel computing capability. A neuromorphic visuosensory and memory system, an important branch of neuromorphic computing, is the basis for AI to perceive, process, and memorize optical information, now still suffering from nonlinearity of synaptic weight, crosstalk issues, and integration incompatibility, hindering the high-level training and inference accuracy. In this work, we propose a new optoelectronic neuromorphic architecture by integrating an electrochromic device and a perovskite photodetector. Ascribing to the superior memory characteristics of the electrochromic device and sensitive light response of the perovskite photodetector, the neuromorphic device shows typical visual synaptic functionalities such as light triggering, neural facilitation, long-term potentiation, and depression (LTP and LTD). Furthermore, by adjusting the intensity and wavelength of external light signals, the visual synaptic function of the device can be modulated, enabling the device to exhibit high weight linearity in all current output ranges and improve information processing capability and image recognition accuracy. Moreover, both the electrochromic and perovskite layers possess the advantage of large area fabrication and integration, which enables the fabrication of large device arrays with high integration compatibility and scalability. In this study, 10 × 10 device arrays are demonstrated and each device shows uniform light responses, memory behaviors, and synaptic performances. MNIST and CIFAR-10 algorithms are used to simulate the image recognition properties of the synaptic architecture, and the calculated recognition accuracy is 97.94 and 91.04%, respectively, with an error less than 2.5%. The proposed artificial visual neuromorphic architecture will provide a potential device prototype for efficient visual neuromorphic systems.

Two-dimensional materials memory devices with floating metal gate for neuromorphic applications

Emerging technologies such as neuromorphic computing and nonvolatile memories based on floating gate field-effect transistors (FETs) hold promise for addressing a wide range of artificial intelligence tasks. For example, neuromorphic computing seeks to emulate the human brain's functionality and employs a device that mimics the role of a synapse in the brain. However, achieving a high current ON/OFF ratio for the program and erase states of nonvolatile memory and neuromorphic computing device with a metal gate is necessary. This study demonstrates a multi-functional device based on heterostructures of transition metal dichalcogenides (TMDCs) with a metal floating gate. Five different channel materials (SnS2, WSe2, MoS2, WS2, and MoTe2) were employed, and hexagonal boron nitride (h-BN) was used as a tunneling layer. The study found that n-type SnS2 exhibits high endurance (15,000 cycles), good retention (2.4 × 105 s), and the highest current ON/OFF ratio (∼2.58 × 108) among the materials for the program and erase states. Moreover, the SnS2 device exhibits synaptic behavior and offers highly stable operation at room temperature. Furthermore, the device shows high linearity in both potentiation and depression, with good retention time and repeatable results with low cycle-to-cycle variations. Additionally, the study used an artificial neural network (ANN) for MNIST simulation of image recognition and achieved the highest accuracy of ∼92 % based on the SnS2 synaptic device experimental results. These findings pave the way for developing nonvolatile memory devices and their applications in brain-inspired neuromorphic computing and artificial intelligence systems.

Advancements in Complementary Metal-Oxide Semiconductor-Compatible Tunnel Barrier Engineered Charge-Trapping Synaptic Transistors for Bio-Inspired Neural Networks in Harsh Environments.

This study aimed to propose a silicon-on-insulator (SOI)-based charge-trapping synaptic transistor with engineered tunnel barriers using high-k dielectrics for artificial synapse electronics capable of operating at high temperatures. The transistor employed sequential electron trapping and de-trapping in the charge storage medium, facilitating gradual modulation of the silicon channel conductance. The engineered tunnel barrier structure (SiO2/Si3N4/SiO2), coupled with the high-k charge-trapping layer of HfO2 and high-k blocking layer of Al2O3, enabled reliable long-term potentiation/depression behaviors within a short gate stimulus time (100 μs), even under elevated temperatures (75 and 125 °C). Conductance variability was determined by the number of gate stimuli reflected in the maximum excitatory postsynaptic current (EPSC) and the residual EPSC ratio. Moreover, we analyzed the Arrhenius relationship between the EPSC as a function of the gate pulse number (N = 1-100) and the measured temperatures (25, 75, and 125 °C), allowing us to deduce the charge trap activation energy. A learning simulation was performed to assess the pattern recognition capabilities of the neuromorphic computing system using the modified National Institute of Standards and Technology datasheets. This study demonstrates high-reliability silicon channel conductance modulation and proposes in-memory computing capabilities for artificial neural networks using SOI-based charge-trapping synaptic transistors.

Spike Optimization to Improve Properties of Ferroelectric Tunnel Junction Synaptic Devices for Neuromorphic Computing System Applications.

The continuous advancement of Artificial Intelligence (AI) technology depends on the efficient processing of unstructured data, encompassing text, speech, and video. Traditional serial computing systems based on the von Neumann architecture, employed in information and communication technology development for decades, are not suitable for the concurrent processing of massive unstructured data tasks with relatively low-level operations. As a result, there arises a pressing need to develop novel parallel computing systems. Recently, there has been a burgeoning interest among developers in emulating the intricate operations of the human brain, which efficiently processes vast datasets with remarkable energy efficiency. This has led to the proposal of neuromorphic computing systems. Of these, Spiking Neural Networks (SNNs), designed to closely resemble the information processing mechanisms of biological neural networks, are subjects of intense research activity. Nevertheless, a comprehensive investigation into the relationship between spike shapes and Spike-Timing-Dependent Plasticity (STDP) to ensure efficient synaptic behavior remains insufficiently explored. In this study, we systematically explore various input spike types to optimize the resistive memory characteristics of Hafnium-based Ferroelectric Tunnel Junction (FTJ) devices. Among the various spike shapes investigated, the square-triangle (RT) spike exhibited good linearity and symmetry, and a wide range of weight values could be realized depending on the offset of the RT spike. These results indicate that the spike shape serves as a crucial indicator in the alteration of synaptic connections, representing the strength of the signals.

All-Solid-State Synaptic Transistors with Lithium-Ion-Based Electrolytes for Linear Weight Mapping and Update in Neuromorphic Computing Systems.

Neuromorphic computing, an innovative technology inspired by the human brain, has attracted increasing attention as a promising technology for the development of artificial intelligence systems. This study proposes synaptic transistors with a Li1-xAlxTi2-x(PO4)3 (LATP) layer to analyze the conductance modulation linearity, which is essential for weight mapping and updating during on-chip learning processes. The high ionic conductivity of the LATP electrolyte provides a large hysteresis window and enables linear weight update in synaptic devices. The results demonstrate that optimizing the LATP layer thickness improves the conductance modulation and linearity of synaptic transistors during potentiation and degradation. A 20 nm-thick LATP layer results in the most nonlinear depression (αd = -6.59), whereas a 100 nm-thick LATP layer results in the smallest nonlinearity (αd = -2.22). Additionally, a device with the optimal 100 nm-thick LATP layer exhibits the highest average recognition accuracy of 94.8% and the smallest fluctuation, indicating that the linearity characteristics of a device play a crucial role in weight update during learning and can significantly affect the recognition accuracy.