Low-power Neuromorphic Computing Research Articles

Ion-migration-induced synaptic plasticity in high ion-storable fluorine graphdiyne for information processing

Neuromorphic devices encounter constraints associated with complementary metal–oxide–semiconductor technology, such as intricate electronics and high power consumption. Recently, solid polymer electrolytes (SPE) have gained attention in electronic devices for constructing artificial synapses, primarily due to their low-voltage operation enabled by ion-assisted signal transmission. This study presents a two-terminal artificial synapse fabricated using fluorine graphdiyne (F-GDY) synthesized through chemical vapor deposition and ion-doped SPE. The device architecture consists of Au/SPE/F-GDY/Si, which operates by ion migration induced by external potential pulses. Electrical measurements are conducted to depict the synaptic plasticity of the devices. Among devices employing different ion-doped SPEs (Li-SPE, Na-SPE, K-SPE, and Ca-SPE), the one utilizing Li-SPE demonstrates the highest synaptic weight. This is attributed to the superior Li+ ion storage capacity of F-GDY. Hence, Li-SPE/F-GDY was chosen for in-depth examinations of synaptic activity presenting long-term potentiation, short-term depression, and pair-pulse facilitation. The device has good durability and stability and can respond to low action potential with power consumption at the pJ level. Furthermore, Modified National Institute of Standards and Technology simulations reveal its learning and pattern recognition capability with 91.3 % accuracy after 10 training epochs. Finally, flexible substrate-based SPE/F-GDY devices integrated with gate electrodes were fabricated to record physiological signals, showing promise for in-sensing applications. This work shows the potential of F-GDY/Li-SPE devices for low-power neuromorphic computing, though real-time parallel processing and multimodal integration (e.g., visual, auditory) remain unexplored. Even so, the biocompatibility and efficient ion-assisted transmission of F-GDY suggest promising future applications in these areas.

Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Networks

Neuromorphic object recognition with spiking neural networks (SNNs) is the cornerstone of low-power neuromorphic computing. However, existing SNNs suffer from significant latency, utilizing 10 to 40 timesteps or more, to recognize neuromorphic objects. At low latencies, the performance of existing SNNs is drastically degraded. In this work, we propose the Shrinking SNN (SSNN) to achieve low-latency neuromorphic object recognition without reducing performance. Concretely, we alleviate the temporal redundancy in SNNs by dividing SNNs into multiple stages with progressively shrinking timesteps, which significantly reduces the inference latency. During timestep shrinkage, the temporal transformer smoothly transforms the temporal scale and preserves the information maximally. Moreover, we add multiple early classifiers to the SNN during training to mitigate the mismatch between the surrogate gradient and the true gradient, as well as the gradient vanishing/exploding, thus eliminating the performance degradation at low latency. Extensive experiments on neuromorphic datasets, CIFAR10-DVS, N-Caltech101, and DVS-Gesture have revealed that SSNN is able to improve the baseline accuracy by 6.55% ~ 21.41%. With only 5 average timesteps and without any data augmentation, SSNN is able to achieve an accuracy of 73.63% on CIFAR10-DVS. This work presents a heterogeneous temporal scale SNN and provides valuable insights into the development of high-performance, low-latency SNNs.

Bipolar Resistive Switching in 2D MoSe2 Grown by Atmospheric Pressure Chemical Vapor Deposition.

Two-dimensional (2D) transition metal dichalcogenides (TMDCs) are highly promising nanomaterials for various electronic devices such as field-effect transistors, junction diodes, tunneling devices, and, more recently, memristors. 2D MoSe2 stands out for having high electrical conductivity, charge carrier mobility, and melting point. While these features make it particularly appropriate as a switching layer in memristive devices, reliable and scalable production of large-area 2D MoSe2 still represents a challenge. In this study, we manufacture 2D MoSe2 films by atmospheric-pressure chemical vapor deposition and investigate them on the atomic scale. We selected and transferred MoSe2 bilayer to serve as a switching layer between asymmetric Au-Cu electrodes in miniaturized crossbar vertical memristors. The electrochemical metallization devices showed forming-free, bipolar resistive switching at low voltages, with clearly identifiable nonvolatile states. Other than low-power neuromorphic computing, low switching voltages approaching the range of biological action potentials could unlock hybrid biological interfaces.

WOx channel engineering of Cu-ion-driven synaptic transistor array for low-power neuromorphic computing

The multilevel current states of synaptic devices in artificial neural networks enable next-generation computing to perform cognitive functions in an energy-efficient manner. Moreover, considering large-scale synaptic arrays, multiple states programmed in a low-current regime may be required to achieve low energy consumption, as demonstrated by simple numerical calculations. Thus, we propose a three-terminal Cu-ion-actuated CuOx/HfOx/WO3 synaptic transistor array that exhibits analogously modulated channel current states in the range of tens of nanoamperes, enabled by WO3 channel engineering. The introduction of an amorphous stoichiometric WO3 channel formed by reactive sputtering with O gas significantly lowered the channel current but left it almost unchanged with respect to consecutive gate voltage pulses. An additional annealing process at 450 °C crystallized the WO3, allowing analog switching in the range of tens of nanoamperes. The incorporation of N gas during annealing induced a highly conductive channel, making the channel current modulation negligible as a function of the gate pulse. Using this optimized gate stack, Poole–Frenkel conduction was identified as a major transport characteristic in a temperature-dependent study. In addition, we found that the channel current modulation is a function of the gate current response, which is related to the degree of progressive movement of the Cu ions. Finally, the synaptic characteristics were updated using fully parallel programming and demonstrated in a 7 × 7 array. Using the CuOx/HfOx/WO3 synaptic transistors as weight elements in multilayer neural networks, we achieved a 90% recognition accuracy on the Fashion-MNIST dataset.

Superlow Power Consumption Memristor Based on Borphyrin-Deoxyribonucleic Acid Composite Films as Artificial Synapse for Neuromorphic Computing.

Memristor synapses based on green and pollution-free organic materials are expected to facilitate biorealistic neuromorphic computing and to be an important step toward the next generation of green electronics. Metalloporphyrin is an organic compound that widely exists in nature with good biocompatibility and stable chemical properties, and has already been used to fabricate memristors. However, the application of metalloporphyrin-based memristors as synaptic devices still faces challenges, such as realizing a high switching ratio, low power consumption, and bidirectional conductance modulation. We developed a memristor that improves the resistive switching (RS) characteristics of Zn(II)meso-tetra(4-carboxyphenyl) porphine (ZnTCPP) by combining it with deoxyribonucleic acid (DNA) in a composite film. The as-fabricated ZnTCPP-DNA-based device showed excellent RS memory characteristics with a sufficiently high switching ratio of up to ∼104, super low power consumption of ∼39.56 nW, good cycling stability, and data retention capability. Moreover, bidirectional conductance modulation of the ZnTCPP-DNA-based device can be controlled by modulating the amplitudes, durations, and intervals of positive and negative pulses. The ZnTCPP-DNA-based device was used to successfully simulate a series of synaptic functions including long-term potentiation, long-term depression, spike time-dependent plasticity, paired-pulse facilitation, excitatory postsynaptic current, and human learning behavior, which demonstrates its potential applicability to neuromorphic devices. A two-layer artificial neural network was used to demonstrate the digit recognition ability of the ZnTCPP-DNA-based device, which reached 97.22% after 100 training iterations. These results create a new avenue for the research and development of green electronics and have major implications for green low-power neuromorphic computing in the future.

Ultrathin SrTiO3-based oxide memristor with both drift and diffusive dynamics as versatile synaptic emulators for neuromorphic computing

Abstract Artificial synapses are electronic devices that simulate important functions of biological synapses, and therefore are the basic components of artificial neural morphological networks for brain-like computing. One of the most important objectives for developing artificial synapses is to simulate the characteristics of biological synapses as much as possible, especially their self-adaptive ability to external stimuli. Here, we have successfully developed an artificial synapse with multiple synaptic functions and highly adaptive characteristics based on a simple SrTiO3/Nb: SrTiO3 heterojunction type memristor. Diverse functions of synaptic learning, such as short-term/long-term plasticity (STP/LTP), transition from STP to LTP, learning–forgetting–relearning behaviors, associative learning and dynamic filtering, are all bio-realistically implemented in a single device. The remarkable synaptic performance is attributed to the fascinating inherent dynamics of oxygen vacancy drift and diffusion, which give rise to the coexistence of volatile- and nonvolatile-type resistive switching. This work reports a multi-functional synaptic emulator with advanced computing capability based on a simple heterostructure, showing great application potential for a compact and low-power neuromorphic computing system.

Bipolar Resistive Switching in TiO2 Artificial Synapse Mimicking Pavlov's Associative Learning.

Memristive devices are among the most emerging electronic elements to realize artificial synapses for neuromorphic computing (NC) applications and have potential to replace the traditional von-Neumann computing architecture in recent times. In this work, pulsed laser deposition-manufactured Ag/TiO2/Pt memristor devices exhibiting digital and analog switching behavior are considered for NC. The TiO2 memristor shows excellent performance of digital resistive switching with a memory window of order ∼103. Furthermore, the analog resistive switching offers multiple conductance levels supporting the development of the bioinspired synapse. A possible mechanism for digital and analog switching behavior in our device is proposed. Remarkably, essential synaptic functions such as pair-pulse facilitation, long-term potentiation (LTP), and long-term depression (LTD) are successfully realized based on the change in conductance through analog memory characteristics. Based on the LTP-LTD, a neural network simulation for the pattern recognition task using the MNIST data set is investigated, which shows a high recognition accuracy of 95.98%. Furthermore, more complex synaptic behavior such as spike-time-dependent plasticity and Pavlovian classical conditioning is successfully emulated for associative learning of the biological brain. This work enriches the TiO2-based resistive random-access memory, which provides information about the simultaneous existence of digital and analog behavior, thereby facilitating the further implementation of memristors in low-power NC.

Room-temperature valley transistors for low-power neuromorphic computing

Valley pseudospin is an electronic degree of freedom that promises highly efficient information processing applications. However, valley-polarized excitons usually have short pico-second lifetimes, which limits the room-temperature applicability of valleytronic devices. Here, we demonstrate room-temperature valley transistors that operate by generating free carrier valley polarization with a long lifetime. This is achieved by electrostatic manipulation of the non-trivial band topology of the Weyl semiconductor tellurium (Te). We observe valley-polarized diffusion lengths of more than 7 μm and fabricate valley transistors with an ON/OFF ratio of 105 at room temperature. Moreover, we demonstrate an ion insertion/extraction device structure that enables 32 non-volatile memory states with high linearity and symmetry in the Te valley transistor. With ultralow power consumption (~fW valley contribution), we enable the inferring process of artificial neural networks, exhibiting potential for applications in low-power neuromorphic computing.

ECRAM Materials, Devices, Circuits and Architectures: A Perspective.

Non-von-Neumann computing using neuromorphic systems based on two-terminal resistive nonvolatile memory elements has emerged as a promising approach, but its full potential has not been realized due to the lack of materials and devices with the appropriate attributes. Unlike memristors, which require large write currents to drive phase transformations or filament growth, electrochemical random access memory (ECRAM) decouples the "write" and "read" operations using a "gate" electrode to tune the conductance state through charge-transfer reactions, and every electron transferred through the external circuit in ECRAM corresponds to the migration of ≈1 ion used to store analogue information. Like static dopants in traditional semiconductors, electrochemically inserted ions modulate the conductivity by locally perturbing a host's electronic structure; however, ECRAM does so in a dynamic and reversible manner. The resulting change in conductance can span orders of magnitude, from gradual increments needed for analog elements, to large, abrupt changes for dynamically reconfigurable adaptive architectures. In this in-depth perspective, the history of ECRAM, the recent progress in devices spanning organic, inorganic, and 2D materials, circuits, architectures, the rich portfolio of challenging, fundamental questions, and how ECRAM can be harnessed to realize a new paradigm for low-power neuromorphic computing are discussed.

A junctionless dual-gate MOSFET-based programmable inverter for secured hardware applications using nitride charge trapping

In this paper we investigate a junction-less dual-gate metal–oxide–semiconductor field effect transistor (JL-DG-MOSFET)-based programmable inverter with an oxide–nitride–oxide (SiO2/Si3N4/SiO2) gate stack, which offers short-/long-term memory as well as logic functionalities depending on charge trapping in the nitride layer. It has been shown that the pulsing interval plays a pivotal role in deciding the short-term plasticity/long-term plasticity window based on the charges trapped/detrapped at/near the oxide–nitride interface. Moreover, we have demonstrated a JL-DG-MOSFET-based complementary metal–oxide–semiconducor inverter with a programmable switching threshold and propose a scheme for secure key generation for authentication. The intra-Hamming distance among the 21 keys generated by the programmable inverter is also depicted to demonstrate the efficacy of the proposed framework. This will eliminate the physical separation between the logic and memory and can offer attractive solutions for silicon-based low-power neuromorphic computing and hardware security.

Integrate-and-Fire Neuron With Li-Based Electrochemical Random Access Memory Using Native Linear Current Integration Characteristics

Neuromorphic computing has gained a considerable research interest due to its potential in realizing highly efficient parallel computations. However, the existing neuromorphic architectures face various drawbacks. In this study, we present an integrate-and-fire (I&F) neuron using a Li-based electrochemical random access memory (Li-ECRAM) to achieve exceptional area efficiency and low-power neuromorphic computing. The proposed Li-ECRAM neuron employs a significantly reduced number of transistors when compared to other novel nonvolatile memory-based I&F neurons due to linear current integration characteristics and a high linear conductance response to the input current. As the integration-type Li-ECRAM is linear, it eliminates the requirement of a nonlinear compensating circuit. Therefore, a Li-ECRAM-based neuron has a simple structure comprising Li-ECRAM, reset transistor, inverter, and pulse generator. Furthermore, we also evaluate the operation speed and energy consumption of the proposed neuron, demonstrating the potential for high-speed and low-power operation. The proposed neuron can be applied in large-scale neuromorphic hardware applications due to the scalability and low energy consumption of Li-ECRAM.

2D Heterostructures for Ubiquitous Electronics and Optoelectronics: Principles, Opportunities, and Challenges.

A grand family of two-dimensional (2D) materials and their heterostructures have been discovered through the extensive experimental and theoretical efforts of chemists, material scientists, physicists, and technologists. These pioneering works contribute to realizing the fundamental platforms to explore and analyze new physical/chemical properties and technological phenomena at the micro-nano-pico scales. Engineering 2D van der Waals (vdW) materials and their heterostructures via chemical and physical methods with a suitable choice of stacking order, thickness, and interlayer interactions enable exotic carrier dynamics, showing potential in high-frequency electronics, broadband optoelectronics, low-power neuromorphic computing, and ubiquitous electronics. This comprehensive review addresses recent advances in terms of representative 2D materials, the general fabrication methods, and characterization techniques and the vital role of the physical parameters affecting the quality of 2D heterostructures. The main emphasis is on 2D heterostructures and 3D-bulk (3D) hybrid systems exhibiting intrinsic quantum mechanical responses in the optical, valley, and topological states. Finally, we discuss the universality of 2D heterostructures with representative applications and trends for future electronics and optoelectronics (FEO) under the challenges and opportunities from physical, nanotechnological, and material synthesis perspectives.

HuRAI: A brain-inspired computational model for human-robot auditory interface

The deep learning era endows immense opportunities for ubiquitous robotic applications by leveraging big data generated from widespread sensors and ever-growing computing capability. While the growing demands for natural human-robot interaction (HRI) as well as concerns for energy efficiency, real-time performance, and data security motive novel solutions. In this paper, we present a brain-inspired spiking neural network (SNN) based Human-Robot Auditory Interface, namely HuRAI. The HuRAI integrates the voice activity detection, speaker localization and voice command recognition systems into a unified framework that can be implemented on the emerging low-power neuromorphic computing (NC) devices. Our experimental results demonstrate superior modeling capabilities of SNNs, achieving accurate and rapid prediction for each task. Moreover, the energy efficiency analysis reveals a compelling prospect, with up to three orders of magnitude energy savings, over the equivalent artificial neural networks that running on the state-of-the-art Nvidia graphics processing unit (GPU). Therefore, integrating the algorithmic power of large-scale SNN models and the energy efficiency of NC devices offers an attractive solution for real-time, low-power robotic applications.

Nanofiber Channel Organic Electrochemical Transistors for Low-Power Neuromorphic Computing and Wide-Bandwidth Sensing Platforms.

Organic neuromorphic computing/sensing platforms are a promising concept for local monitoring and processing of biological signals in real time. Neuromorphic devices and sensors with low conductance for low power consumption and high conductance for low‐impedance sensing are desired. However, it has been a struggle to find materials and fabrication methods that satisfy both of these properties simultaneously in a single substrate. Here, nanofiber channels with a self‐formed ion‐blocking layer are fabricated to create organic electrochemical transistors (OECTs) that can be tailored to achieve low‐power neuromorphic computing and fast‐response sensing by transferring different amounts of electrospun nanofibers to each device. With their nanofiber architecture, the OECTs exhibit a low switching energy of 113 fJ and operate within a wide bandwidth (cut‐off frequency of 13.5 kHz), opening a new paradigm for energy‐efficient neuromorphic computing/sensing platforms in a biological environment without the leakage of personal information.

Recent progress on optoelectronic synaptic devices

Neuromorphic (brain-like) computing has great potential to solve the von Neumann bottleneck due to its self-adaptive learning, high-parallel computing capability, and low-power consumption. Realization of neuromorphic computing depends on the development of synaptic devices that mimic biological synapses. Initially, synaptic devices were electronic, and such devices face significant challenges relative to optimization of bandwidth, connectivity, and density. It has been recently shown that the incorporation of light to make optoelectronic synaptic devices brings new opportunities for the development of synaptic devices. On one hand, light enables high bandwidth, low crosstalk, low energy consumption, and no delay. On the other hand, optoelectronic devices can be used to simulate special neurobehavioral functions, such as vision. As the basis of optoelectronic integrated neural networks, optoelectronic synaptic devices are expected to greatly contribute to the development of high-performance and low-power neuromorphic computing. In this review we introduce the basic properties of optoelectronic synaptic devices. Different types and applications that have been reported for optoelectronic devices are discussed. In addition, future prospects for the development of optoelectronic synaptic devices is outlined.

Vacancy-Induced Synaptic Behavior in 2D WS2 Nanosheet-Based Memristor for Low-Power Neuromorphic Computing.

Memristors with nonvolatile memory characteristics have been expected to open a new era for neuromorphic computing and digital logic. However, existing memristor devices based on oxygen vacancy or metal-ion conductive filament mechanisms generally have large operating currents, which are difficult to meet low-power consumption requirements. Therefore, it is very necessary to develop new materials to realize memristor devices that are different from the mechanisms of oxygen vacancy or metal-ion conductive filaments to realize low-power operation. Herein, high-performance and low-power consumption memristors based on 2D WS2 with 2H phase are demonstrated, which show fast ON (OFF) switching times of 13 ns (14 ns), low program current of 1 µA in the ON state, and SET (RESET) energy reaching the level of femtojoules. Moreover, the memristor can mimic basic biological synaptic functions. Importantly, it is proposed that the generation of sulfur and tungsten vacancies and electron hopping between vacancies are dominantly responsible for the resistance switching performance. Density functional theory calculations show that the defect states formed by sulfur and tungsten vacancies are at deep levels, which prevent charge leakage and facilitate the realization of low-power consumption for neuromorphic computing application.

Vertical MoS2 Double-Layer Memristor with Electrochemical Metallization as an Atomic-Scale Synapse with Switching Thresholds Approaching 100 mV.

Atomically thin two-dimensional (2D) materials-such as transition metal dichalcogenide (TMD) monolayers and hexagonal boron nitride (hBN)-and their van der Waals layered preparations have been actively researched to build electronic devices such as field-effect transistors, junction diodes, tunneling devices, and, more recently, memristors. Two-dimensional material memristors built in lateral form, with horizontal placement of electrodes and the 2D material layers, have provided an intriguing window into the motions of ions along the atomically thin layers. On the other hand, 2D material memristors built in vertical form with top and bottom electrodes sandwiching 2D material layers may provide opportunities to explore the extreme of the memristive performance with the atomic-scale interelectrode distance. In particular, they may help push the switching voltages to a lower limit, which is an important pursuit in memristor research in general, given their roles in neuromorphic computing. In fact, recently Akinwande et al. performed a pioneering work to demonstrate a vertical memristor that sandwiches a single MoS2 monolayer between two inert Au electrodes, but it could neither attain switching voltages below 1 V nor control the switching polarity, obtaining both unipolar and bipolar switching devices. Here, we report a vertical memristor that sandwiches two MoS2 monolayers between an active Cu top electrode and an inert Au bottom electrode. Cu ions diffuse through the MoS2 double layers to form atomic-scale filaments. The atomic-scale thickness, combined with the electrochemical metallization, lowers switching voltages down to 0.1-0.2 V, on par with the state of the art. Furthermore, our memristor achieves consistent bipolar and analogue switching, and thus exhibits the synapse-like learning behavior such as the spike-timing dependent plasticity (STDP), the very first STDP demonstration among all 2D-material-based vertical memristors. The demonstrated STDP with low switching voltages is promising not only for low-power neuromorphic computing, but also from the point of view that the voltage range approaches the biological action potentials, opening up a possibility for direct interfacing with mammalian neuronal networks.

Organic electronics for neuromorphic computing

Neuromorphic computing could address the inherent limitations of conventional silicon technology in dedicated machine learning applications. Recent work on silicon-based asynchronous spiking neural networks and large crossbar arrays of two-terminal memristive devices has led to the development of promising neuromorphic systems. However, delivering a compact and efficient parallel computing technology that is capable of embedding artificial neural networks in hardware remains a significant challenge. Organic electronic materials offer an attractive option for such systems and could provide biocompatible and relatively inexpensive neuromorphic devices with low-energy switching and excellent tunability. Here, we review the development of organic neuromorphic devices. We consider different resistance-switching mechanisms, which typically rely on electrochemical doping or charge trapping, and report approaches that enhance state retention and conductance tuning. We also discuss the challenges the field faces in implementing low-power neuromorphic computing, such as device downscaling and improving device speed. Finally, we highlight early demonstrations of device integration into arrays, and consider future directions and potential applications of this technology.

In situ investigation of the channel conductance of a Li1−xCoO2 (0 < x < 0.5) ionic-electronic transistor

An ion gated transistor is shown to have an analog electronic channel resistance that is dependent on the ion concentration in a solid state device. The ionic transistor made from a common battery cathode material, LiCoO2, is investigated for use in devices that exploit the interaction between ions and electrons with applications in low-power neuromorphic computing and non-volatile memory. The majority of the resistance change in LiCoO2 occurs close to the stoichiometric point, and thus, nanoscale LiCoO2-based ionic electronic devices are expected to consume minimal power and avoid structural phase changes leading to improved reliability.