Linear Weight Update Synaptic Responses in Ferrimagnetic Neuromorphic Devices

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.

Due to the low carrier scattering and scale‐down capability, two‐dimensional (2D) materials are promising for building high‐temperature neuromorphic electronics that are highly needed for performing complex tasks above 125°C. However, current 2D high‐temperature neuromorphic devices based on conventional resistive switching mechanisms still have key problems, e.g., severe gate leakage in three‐terminal devices and a limited number of resistance states in two‐terminal devices at high operating temperatures. Here, we report a gate‐free, high‐temperature MoS 2 neuromorphic device with up to 256 tunable resistance states, representing the state‐of‐the‐art resistance state number in a two‐terminal device operating at high temperatures. In addition to the multi‐state function, the device also has an enhanced resistive switching ratio of ∼10 3 at 200°C and simulates diverse synaptic plasticities at 350°C. Such superior performance is enabled by Schottky barrier modulation through thermal‐activated directional migration of sulfur vacancies. The device further demonstrates remarkable potential for high‐temperature neuromorphic computing in handwritten digit recognition and reservoir‐computing‐based temporal data processing. This work provides a new strategy for developing high‐temperature neuromorphic devices based on 2D materials.

Linear weights modulation in neuromorphic memristor plays an important role in high-accuracy image recognition task. Herein, a Li+ doped organic artificial memristor for neuromorphic computing was proposed for linear weights update, which shows active ions diffusive dynamics as Ca2+ diffusion in biological synapse. The memristor exhibits gradual resistive switching, multi-state storage and typical synaptic behaviors. In addition, the synaptic learning capability of letter “T” was demonstrated in a memristors array. By designing consecutive pulse waveforms with enhanced amplitude, the linearity of memristor for weight update in long-term potentiation and depression (LTP/LTD) could be improved from 6.8 to 0.4. Based on the great nonlinearity factor in LTP ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha _{\text {p}}={1.5}$ </tex-math></inline-formula> ) and LTD ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha _{\text {d}}={0.4}$ </tex-math></inline-formula> ), face recognition was achieved with high accuracy of 96% by artificial neural network consisting of ion doped memristors. The ion doped organic memristor with highly linear weights update provides guidelines for the development of bio-inspired ion diffusive neuromorphic computing system.

Engineering of TiN/ZnO/SnO2/ZnO/Pt multilayer memristor with advanced electronic synapses and analog switching for neuromorphic computing

Artificial synaptic simulating pain-perceptual nociceptor and brain-inspired computing based on Au/Bi3.2La0.8Ti3O12/ITO memristor

All-in-one metal-oxide heterojunction artificial synapses for visual sensory and neuromorphic computing systems

Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. In my talk, I will review the latest advances in neuromorphic computing architectures based on deep neural networks implemented using CMOS and memristors and describe the challenges in achieving both high accuracy and energy efficiency using these devices. I will then discuss an alternative approach based on the non-volatile redox memory (NVRM): a device with a resistance switching mechanism fundamentally different from existing memristors, involving the reversible, electrochemical reduction/oxidation of a material to tune its electronic conductivity. The first type of NVRM that I will describe is based upon the intercalation of Li-ion dopants into a channel of Li1−xCoO2. This Li-ion synaptic transistor for analog computing (LISTA) switches at low voltage (mVs) and energy, displays hundreds of distinct, non-volatile conductance states within a 1V range, and achieves high classification accuracy when implemented in neural network simulations1. The second type of NVRM I will describe operates on a similar principle but is based on the polymer system PEDOT:PSS, and which we call the electrochemical neuromorphic organic device (ENODe) 2. Plastic ENODes are fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with three-dimensional architectures, opening a path towards extreme interconnectivity comparable to the human brain. (1) E. J. Fuller, F. El Gabaly, F. Léonard, S. Agarwal, S. J. Plimpton, R. B. Jacobs-Gedrim, C. D. James, M. J. Marinella and A. A. Talin, Advanced Materials 29, 1604310 2017. (2) Y. B. van de Burgt, E. Lubberman, E. J. Fuller, S.T. Keene, G. C. Faria, S. Agarwal, M. J. Marinella, A. A. Talin* and A. Salleo*, Nature Materials 16, 414 2017.

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

An oxygen-based ionic synaptic transistor (O-IST) is a promising synaptic element for neuromorphic computing. In this study, we demonstrated that the density of the electrolyte plays a key role in achieving excellent synaptic characteristics in an O-IST. In a Pr0.7Ca0.3MnO3-based O-IST, we precisely controlled the density of the HfOx electrolyte and found that a low-density electrolyte could improve the ion mobility. Owing to the improved ion mobility and controlled ion migration, we demonstrated that excellent synaptic characteristics, such as a wide dynamic range, linear weight update, low operating voltage operations, and stable cyclic operation, were achieved. Finally, we confirmed an improved pattern recognition accuracy using an O-IST with an HfOx electrolyte of optimal density.

In the post-Moore’s Law era, conventional Von Neumann architectures face critical limitations, such as the “memory wall” and excessive power consumption, particularly when processing unstructured data. Neuromorphic computing, inspired by the human brain, offers a promising solution through parallel processing and adaptive learning. Among the candidates for artificial synapses, memristors based on two-dimensional MXenes (specifically Ti3C2Tx) have attracted significant attention due to their unique layered structure, high metallic conductivity, and tunable physicochemical properties. This review provides a comprehensive analysis of MXene-based memristors, from material synthesis to system-level applications. We examine how different synthesis strategies, including etching methods, directly influence device performance and elucidate the underlying resistive switching mechanisms driven by ion migration, valence change, and interfacial processes. Furthermore, the review demonstrates the efficacy of MXenes in emulating biological synaptic functions—such as spike-timing-dependent plasticity (STDP) and long-term potentiation/depression (LTP/LTD)—and their application in tasks like handwritten digit recognition. Finally, we highlight emerging frontiers in flexible electronics and in-sensor computing, offering insights into the future trajectory of integrated sensing, memory, and computation.

2D metal–organic frameworks (2D‐MOFs) have been extensively studied as promising materials in the fields of electrocatalysis, drug delivery, electronic devices, etc. However, few studies have explored the application potential of 2D‐MOFs in novel neuromorphic computing devices. Herein, an optoelectronic neuromorphic transistor based on a 2D‐MOF/polymer charge‐trapping layer is reported. It is found that the large specific surface area, stable crystal structure, and highly accessible active sites in 2D‐MOFs make them excellent charge‐trapping materials for the devices, which are beneficial for mimicking the memory and learning functions observed in the organism's nervous systems. Different types of synaptic behaviors have been realized in the 2D‐MOF‐based neuromorphic devices under stimuli signal, e.g., paired‐pulse facilitation, excitatory postsynaptic current, short‐term memory, and long‐term memory. More interestingly, emotion‐adjustable learning behavior is realized by changing the value of the source–drain voltage. This work can shed light on the application of 2D‐MOFs in neuromorphic computing and will contribute to the further development of neuromorphic computing devices. An interactive preprint version of the article can be found at DOI: https://doi.org/10.22541/au.165530836.62586068/v1.

Neuromorphic computing offers energy‐efficient computations for large‐scale data processing compared to conventional von Neumann computing. The artificial synapse, a key element for learning and memory operations in neuromorphic computing, requires multi‐state characteristics and the capability to change and store its states. The implementation of hardware‐based artificial synapses using nonvolatile memory provides significant advantages in terms of energy consumption and circuit area compared to their currently employed CMOS‐based counterparts. In this regard, spintronic devices have emerged as a promising candidate due to their desirable properties for artificial synapses, including multilevel formability, non‐volatility, and outstanding writing performance. In this study, spintronic artificial synapses utilizing voltage‐controlled multilevel magnetic states and energy‐ and area‐efficient artificial neural network architectures associated with them are demonstrated. The multilevel states are created by gradually modulating the magnetic easy‐axis orientation from perpendicular to in‐plane and vice versa, which is achieved either by sequentially applying gate voltage pulses or by adjusting the pulse width of the gate voltage. Based on these spintronic artificial synapses, convolutional neural network (CNN) and spiking neural network (SNN) architectures are constructed, demonstrating high recognition accuracy for the MNIST dataset with improved energy efficiency and a reduced circuit area.

Memristors with tunable conductance characteristics have attracted great attention in high density memory and neuromorphic computing. However, the dynamics of conductance change for filamentary-type memristors is generally asymmetric: The set transition is quite abrupt, while the reset transition is usually gradual, which is a big challenge to achieve continuous conductance tuning characteristics in both set and reset processes. In this work, we demonstrated an HfO2/TiOx (10 nm/10 nm) bilayer structure memristor with the feature of bidirectional conductance tuning (a gradual increase or decrease in conductance) in a simple pulse-train operation mode. A series of voltage pulses with specific amplitude and a fixed width of 50 ns were used to realize the characteristics of bidirectional conductance tuning. By further optimizing the pulse amplitude conditions, such as −1.1 V/50 ns for the set process and 1.3–1.4 V/50 ns for the reset process, the conductance of the memristor can be tuned almost linearly with the input pulse voltage. Such linear conductance update is highly desired for improving the fault tolerance ability in massive data storage or neuromorphic computing.

In the tide of artificial intelligence evolution, the demand for data computing has exploded, and the von Neumann architecture computer with separate memory and computing units require cumbersome data interaction, which leads to serious degradation in performance and efficiency. Biologically inspired neuromorphic engineering performs digital/analog computations in memory, with massive parallelism and high energy efficiency, making it a promising candidate to get out of the woods. Memristive device‐based artificial synapses and neurons are building blocks to form hardware neural networks for computing acceleration. In addition, it enables the implementation of integrated bionic perception and motion systems to mimic the human peripheral nervous system for information sensing and processing. Herein, the biological basis and inspiration are described first, and the memristive synapses and circuit‐emulation neurons used for neuromorphic engineering are addressed and evaluated as well as the mechanisms. The computational acceleration and bionic perception motion integration of neuromorphic systems are discussed. Finally, the challenges and opportunities for neuromorphic engineering to accelerate computation and enrich biomimetic perception motion functions are prospected, and it is hoped that light is shed on future advances.

The human brain, with high energy‐efficient and parallel processing ability, inspires to mitigate power issues perplexing von Neumann architecture. As one of the essential components constructing the human brain, the emulation of biological synapses exploiting electronic devices consuming power at a biological level lays the foundation for the implementation of energy‐efficient neuromorphic computing. Besides, signal matching between biologically‐related stimuli and the driving voltage of artificial synapses helps to realize intelligent neuromorphic interfaces and sustainable energy. Here, ultra‐sensitive artificial synapse stimulated at 1 mV with energy consumption of 132 attojoule/synaptic event is demonstrated. Biological signal matching and low power application are realized simultaneously based on sodium acetate (NaAc) doped polyvinyl alcohol (PVA) electrolyte. The biphasic current, which comprises the electrical‐ and ion‐mediation current component, contributes to enrich synaptic functions compared to monophasic synaptic behavior. Moreover, freestanding NaAc‐doped PVA membrane functions as both dielectric layer and mechanical support and facilitates to achieve flexible, transferable artificial synapse, which maintains functional stability at an ultralow voltage and power even after bending tests. Thus, encompassing superior sensitivity, low energy, and multiple functionalities with flexible, self‐supported, biocompatible property, takes a step to construct energetically‐efficient, complex neuromorphic systems for wearable, implantable medicines as well as smart bio‐electronic interfaces.