Search

With the growing prevalence of neuromorphic computing algorithms, there is a growing need for electronic synaptic devices. In this study, using Li4+ x Ti5O12 (LTO) as the resistive switching layer, C as the lithium ions storage layer, and Li1+ x Al x Ti2− x (PO4)3 (LATP) as ions transmission layer, a synaptic device is designed with the structure of Pt/C/LATP/LTO/PtSi to imitate the lithium-ion battery. Variation of the thickness of the LATP layer in the LTO device is explored to show the impact on the device's synaptic performance. With a LATP thickness of 100 nm, the LTO synaptic device exhibits a high potentiation/depression cyclic stability of over 50 cycles, improved potentiation/depression linearity and smoothness. The synaptic potentiation/depression is ascribed to migration of lithium ions from the LTO layer. A conductance relaxation characteristic of the device is explained by battery self-discharge phenomenon. The battery effect in the LTO device also led to generation of electromotive force. The study of battery-imitating LTO synaptic device offers new perspectives on the connection between battery and analog synaptic device. [ABSTRACT FROM AUTHOR]

To achieve cost‐effectiveness, researchers are exploring various memristors for their adaptation in neuromorphic computing. Recent studies have focused on developing versatile functioning singular memristors, such as those involved in on‐receptor computing, which integrates sensory functions into current neuromorphic computing paradigms. Additionally, adaptations like reservoir computing are being investigated for computing systems. In this study, a memristor composed of a stack of Ti/NbOx/Pt layers is fabricated to explore multifunctional behaviors within a single memristor. By applying bias toward the top Ti electrode, gradual current changes with volatile features are demonstrated, revealing an ion‐migration‐based nonfilamentary switching memristor. Leveraging this volatile functionality, an artificial nociceptor is first implemented, demonstrating key functions of biological nociceptors including thresholding, relaxation, no‐adaptation, and sensitization. Subsequently, synapse emulation akin to the biological brain is achieved through easy conductance potentiation and depression with diverse synapse functions, enabling the memristor to mimic learning activities with spike firing. Lastly, computational applications are explored by adapting edge computing and multi‐bit reservoir computing, expanding the memristor's applications across diverse fields with versatile behaviors. [ABSTRACT FROM AUTHOR]

Bioinspired approaches tend to mimic some biological functions for the purpose of creating more efficient and robust systems. These can be implemented in both software and hardware designs. A neuromorphic software part can include, for example, Spiking Neural Networks (SNNs) or event-based representations. Regarding the hardware part, we can find different sensory systems, such as Dynamic Vision Sensors, touch sensors, and actuators, which are linked together through specific interface boards. To run real-time SNN models, specialised hardware such as SpiNNaker, Loihi, and TrueNorth have been implemented. However, neuromorphic computing is still in development, and neuromorphic platforms are still not easily accessible to researchers. In addition, for Neuromorphic Robotics, we often need specially designed and fabricated PCBs for communication with peripheral components and sensors. Therefore, we developed an all-in-one neuromorphic system that emulates neuromorphic computing by running a Virtual Machine on a conventional low-power CPU. The Virtual Machine includes Python and Brian2 simulation packages, which allow the running of SNNs, emulating neuromorphic hardware. An additional, significant advantage of using conventional hardware such as Raspberry Pi in comparison to purpose-built neuromorphic hardware is that we can utilise the built-in physical input–output (GPIO) and USB ports to directly communicate with sensors. As a proof of concept platform, a robotic goalkeeper has been implemented, using a Raspberry Pi 5 board and SNN model in Brian2. All the sensors, namely DVS128, with an infrared module as the touch sensor and Futaba S9257 as the actuator, were linked to a Raspberry Pi 5 board. We show that it is possible to simulate SNNs on a conventional low-power CPU running real-time tasks for low-latency and low-power robotic applications. Furthermore, the system excels in the goalkeeper task, achieving an overall accuracy of 84% across various environmental conditions while maintaining a maximum power consumption of 20 W. Additionally, it reaches 88% accuracy in the online controlled setup and 80% in the offline setup, marking an improvement over previous results. This work demonstrates that the combination of a conventional low-power CPU running a Virtual Machine with only selected software is a viable competitor to neuromorphic computing hardware for robotic applications. [ABSTRACT FROM AUTHOR]

Integrating RGB and Event (RGBE) multi-domain information obtained by high-dynamic-range and temporal-resolution event cameras has been considered an effective scheme for robust object tracking. However, existing RGBE tracking methods have overlooked the unique spatio-temporal features over different domains, leading to object tracking failure and ineffeciency, especally for objects against complex backgrounds. To address this problem, we propose a novel tracker based on adaptive-time feature extraction hybrid networks, namely Siamese Event Frame Tracker (SiamEFT), which focuses on the effective representation and utilization of the diverse spatio-temporal features of RGBE. We first design an adaptive-time attention module to aggregate event data into frames based on adaptive-time weights to enhance information representation. Subsequently, the SiamEF module and cross-network fusion module combining artificial neural networks and spiking neural networks hybrid network are designed to effectively extract and fuse the spatio-temporal features of RGBE. Extensive experiments on two RGBE datasets (VisEvent and COESOT) show that the SiamEFT achieves a success rate of 0.456 and 0.574, outperforming the state-of-the-art competing methods and exhibiting a 2.3-fold enhancement in effeciency. These results validate the superior accuracy and effeciency of SiamEFT in diverse and challenging scenes. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) have garnered significant attention due to their notable energy efficiency. However, conventional SNNs rely on spike firing frequency to encode information, necessitating a fixed sampling time and leaving room for further optimization. This study presents a novel approach to reduce sampling time and conserve energy by extracting early prediction results from the intermediate layer of the network and integrating them with the final layer's predictions in a Bayesian fashion. Experimental evaluations conducted on image classification tasks using MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate the efficacy of our proposed method when applied to VGGNets and ResNets models. Results indicate a substantial energy reduction of 38.8% in VGGNets and 48.0% in ResNets, illustrating the potential for achieving significant efficiency gains in spiking neural networks. These findings contribute to the ongoing research in enhancing the performance of SNNs, facilitating their deployment in resource-constrained environments. Our code is available on GitHub: https://github.com/hanebarla/BayesianSpikeFusion. [ABSTRACT FROM AUTHOR]

Owing 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. [ABSTRACT FROM AUTHOR]

The rapid advancement of neuromorphic computing demands innovative hardware solutions capable of efficiently mimicking the functionality of biological neural systems. In this context, dynamic memristors have emerged as promising candidates for realizing neuromorphic reservoir computing (RC) architectures. The dynamic memristors characterized by their ability to exhibit nonlinear conductance variations and transient memory behaviors offer unique advantages for constructing RC systems. Unlike recurrent neural networks (RNNs) that face challenges such as vanishing or exploding gradients during training, RC leverages a fixed‐size reservoir layer that acts as a nonlinear dynamic memory. Researchers can capitalize on their adaptable and efficient characteristics by integrating dynamic memristors into RC systems to enable rapid information processing with low learning costs. This perspective provides an overview of the recent developments in dynamic memristors and their applications in neuromorphic RC. It highlights their potential to revolutionize artificial intelligence hardware by offering faster learning speeds and enhanced energy efficiency. Furthermore, it discusses challenges and opportunities associated with integrating dynamic memristors into RC architectures, paving the way for developing next‐generation cognitive computing systems. [ABSTRACT FROM AUTHOR]

A long-standing research goal is to develop computing technologies that mimic the brain's capabilities by implementing computation in electronic systems directly inspired by its structure, function, and operational mechanisms, using low-power, spike-based neural networks. The Loihi neuromorphic processor provides a low-power, large-scale network of programmable silicon neurons for brain-inspired artificial intelligence applications. This paper exploits the Loihi processors and a theory-guided methodology to enable unsupervised learning of spike patterns. Our method ensures efficient and rapid selection of the network's hyperparameters, enabling the neuromorphic processor to generate attractor states through real-time unsupervised learning. Precisely, we follow a fast design process in which we fine-tune network parameters using mean-field theory. Moreover, we measure the network's learning ability regarding its error correction and pattern completion aptitude. Finally, we observe the dynamic energy consumption of the neuron cores for each millisecond of simulation equal to 23 μ J/time step during the learning and recall phase for four attractors composed of 512 excitatory neurons and 256 shared inhibitory neurons. This study showcases how large-scale, low-power digital neuromorphic processors can be quickly programmed to enable the autonomous generation of attractor states. These attractors are fundamental computational primitives that theoretical analysis and experimental evidence indicate as versatile and reusable components suitable for a wide range of cognitive tasks. [ABSTRACT FROM AUTHOR]

Perovskite‐oxide‐based ferroelectric tunnel junctions (FTJs) hold great potential for applications in non‐volatile memory and neuromorphic computing due to their unique properties. However, the challenges in synthesizing high crystalline quality perovskite oxides directly on silicon wafer limit the applications of these FTJs in conventional Si‐based integrated circuits, let alone the neural networks. Herein, perovskite oxide FTJs with an ON/OFF ratio up to 1.2×106, writing/erasing speed down to 1 nanosecond, and cycling endurance (>106) are achieved by integrating ultrathin freestanding ferroelectric perovskite oxide membranes directly on silicon wafers using a wet‐transfer method. Moreover, synapses based on these FTJs exhibit long‐term plasticity. For handwritten digits recognition task, the convolutional neural network (CNN) simulation is implemented achieving a recognition accuracy up to 98.9% based on the experimental performance, close to the result of 99.2% by software‐floating‐point‐based CNN. This work sheds light on the integration of ferroelectric perovskite oxides directly on silicon for high‐performance FTJ‐based non‐volatile memory and synaptic devices. [ABSTRACT FROM AUTHOR]

Recent trends have shown that autonomous agents, such as Autonomous Ground Vehicles (AGVs), Unmanned Aerial Vehicles (UAVs), and mobile robots, effectively improve human productivity in solving diverse tasks. However, since these agents are typically powered by portable batteries, they require extremely low power/energy consumption to operate in a long lifespan. To solve this challenge, neuromorphic computing has emerged as a promising solution, where bio-inspired Spiking Neural Networks (SNNs) use spikes from event-based cameras or data conversion pre-processing to perform sparse computations efficiently. However, the studies of SNN deployments for autonomous agents are still at an early stage. Hence, the optimization stages for enabling efficient embodied SNN deployments for autonomous agents have not been defined systematically. Toward this, we propose a novel framework called SNN4Agents that consists of a set of optimization techniques for designing energy-efficient embodied SNNs targeting autonomous agent applications. Our SNN4Agents employs weight quantization, timestep reduction, and attention window reduction to jointly improve the energy efficiency, reduce the memory footprint, optimize the processing latency, while maintaining high accuracy. In the evaluation, we investigate use cases of event-based car recognition, and explore the trade-offs among accuracy, latency, memory, and energy consumption. The experimental results show that our proposed framework can maintain high accuracy (i.e., 84.12% accuracy) with 68.75% memory saving, 3.58x speed-up, and 4.03x energy efficiency improvement as compared to the state-of-the-art work for the NCARS dataset. In this manner, our SNN4Agents framework paves the way toward enabling energy-efficient embodied SNN deployments for autonomous agents. [ABSTRACT FROM AUTHOR]

Memristors have diverse potential for improving data storage through linear memory control and synaptic operation in AI and neuromorphic computing. Prior research on optimizing memristors in next‐generation devices has generally indicated that emerging arrays and vertical structures can improve memory density, although special fabrication steps are required to realize improved operation. Until now, many obstructions, such as the sneak path current and forming processes from the initial device in array structure operation at the device level, have limited the development of array‐based memristor devices for further progressing circuits and integrated design. In this paper, memristor array studies are examined that have suggested solutions for sneak path current and forming operation problems at the device level. Ultimately, representative solutions are proposed to progress memristors into array structures by introducing the latest research on one diode‐one RRAM (1D1R), one selector‐one RRAM (1S1R), overshoot suppressed RRAM (OSRRAM), self‐rectifying cell (SRC), charge trap memory (CTM) and their applications. Additionally, essential details demonstrating the practical implementation of these devices in crossbar array memory are investigated. Finally, the advantages and perspectives of these array‐based memristor solutions are summarized. [ABSTRACT FROM AUTHOR]

Neuromorphic devices constitute a novel approach to computing that takes inspiration from the brain to unify the processing and storage units. Memories based on phase‐change materials (PCMs) are potential candidates for such devices due to their non‐volatility and excellent scalability, however their use is hindered by their conductance variability and temporal drift in resistance. Recently, it has been shown that the utilization of phase‐change heterostructures consisting of nanolayers of the Sb2Te3 PCM interleaved with a transition‐metal dichalcogenide, acting as a confinement material, strongly mitigates these problems. In this work, superlattice heterostructures made of TiTe2 and two prototypical PCMs, respectively GeTe and Ge2Sb2Te5 are considered. By performing ab initio molecular dynamics simulations, it is shown that it is possible to switch the PCMs without destroying the superlattice structure and without diffusion of the atoms of the PCM across the TiTe2 nanolayers. In particular, the model containing Ge2Sb2Te5 shows weak coupling between the two materials during the switching process, which, combined with the high stability of the amorphous state of Ge2Sb2Te5, makes it a very promising candidate for neuromorphic computing applications. [ABSTRACT FROM AUTHOR]

The advent of big data and the Internet of Things has created urgent demands for in‐sensor computing hardware with multimodal perception that can effectively resolve the inefficiency, high latency, and excessive energy consumption challenges faced by conventional sensory systems. Here, a simple‐structured optoelectronic synaptic device of In2O3·SnO2/Nb:SrTiO3 (ITO/NSTO) heterostructure is proposed, which vividly demonstrates in‐sensor computing and multimodal perception capabilities. First, with the ingenious synaptic responses of the device under both optical and electrical stimuli, a multimodal in‐sensor neuromorphic computing system capable of concurrently perceiving and processing visual and auditory information is constructed. Using this multimodal system to perform a human emotion recognition task, the misjudgment arising from single‐modal cognition can thereby be effectively avoided. Second, utilizing the integrated sensing and processing functions, along with the dynamic memories of the device array, a neuromorphic vision system is implemented for real‐time monitoring of moving vehicles, which displays high recognition efficiency and accuracy. This research not only provides an optoelectronic synaptic device that is low‐cost and easy to mass‐produce, but also paves the way for next‐generation in‐sensor computing that can efficiently process multimodal signals. [ABSTRACT FROM AUTHOR]

p‐type 2D ferroelectric semiconductors (2D FeSs) play an increasingly essential role in the advanced nonvolatile and morphotropic beyond‐Moore electronic devices with high performance and low power consumption. But reliable p‐type 2D FeS with holes as majority carriers are still scarce. Herein, the first experimental realization of room‐temperature ferroelectricity in van der Waals layered β‐In1.75Sb0.25Se3 down to few layer is reported. The origin of ferroelectricity in β‐In1.75Sb0.25Se3 comes from aliovalent elemental substitution, antimony substituting to the indium sites (SbIn), changing the local environment of the central‐layer Se atoms. Thanks to the intrinsic ferroelectric and semiconducting natures, FeS field‐effect transistor (FeSFET) devices based on β‐In1.75Sb0.25Se3 exhibit reconfigurable, multilevel nonvolatile memory (NVM) states, which can be successively modulated by gate voltage stimuli. Furthermore, the inherent operation mechanism, due to the switchable polarization, indicates that a neuromorphic memory is also possible with 2D FeSFETs. These presented results facilitate the technological implementation of versatile 2D FeS devices for next‐generation logic‐in‐memory approach for Internet‐of‐Things entities. [ABSTRACT FROM AUTHOR]

Currently, AI-designed systems in which, given a certain input or prompt, the system returns an output or response are becoming very popular. A chatbot is an example of this kind of system. However, human beings, besides processing the input stimuli or information adequately, are also capable of simultaneously expressing an emotional response to that input information. This is a major factor in the survival of our species. For years, bio-inspired AI models have been proposed in order to make AI systems more human-like. Paradigms, such as neuromorphic computing, represent an example of this trend. In this paper, we propose a new approach that we have termed hormone-morphic by designing a chatbot, Fattybot, with which it is possible to have a conversation. However, since Fattybot is endowed with both a hormonal and immune system, it can feel anxiety or some other altered condition during a conversation, which induces the chatbot to eat compulsively. The ultimate goal of the work is to propose AI systems that not only process information but also experience some of the emotional traits of human beings. In this paper, several simulation experiments are performed showing the usefulness of this approach, for example, in the simulation of a virtual patient. [ABSTRACT FROM AUTHOR]

To improve neuromorphic computing performance, neuromorphic system components should mimic the behaviors of organic systems. In this study, a synaptic a-Si:H/a-Ga2O3 phototransistor featuring all-optical and -electrical emulation is fabricated in a manner advantageous for complementary metal-oxide-semiconductor process integration. The phototransistor exhibits excitatory and inhibitory synaptic behaviors under stimulation by both optical and electrical signals. It mimics several essential synaptic functions, including excitatory postsynaptic current, inhibitory postsynaptic current, short-term memory, long-term memory, paired-pulse facilitation, and spike-timing-dependent plasticity. The optical and electrical modulation mechanisms are confirmed to arise from the a-Si:H/a-Ga2O3 heterojunction structure and interface effects, and the device is shown to operate at low power in both optical and electrical modes. The all-optical weight modulation function is applied to the wavelength-differential behavior response of zebrafish, successfully mimicking the color perception process of the organism. Finally, to verify the translation of the optoelectrical-derived synaptic behaviors of the phototransistor into artificial neuromorphic computation, handwritten digit image recognition of the Modified National Institute of Standards and Technology dataset is performed by a convolutional neural network, with a demonstrated average learning accuracy of 98.46%. These findings verify the applicability of the synaptic a-Si:H/a-Ga2O3 phototransistor in neuromorphic computing. [ABSTRACT FROM AUTHOR]

Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials. These networks harness the distinctive characteristics of physical systems to carry out computations effectively, potentially surpassing the constraints of conventional digital neural networks. A recent advancement known as “physical self-learning” aims to achieve learning through intrinsic physical processes rather than relying on external computations. This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems. Prevailing learning strategies that contribute to the realization of physical self-learning are discussed. Despite challenges in understanding the fundamental mechanism of learning, this work highlights the progress towards constructing intelligent hardware from the ground up, incorporating embedded self-organizing and self-adaptive dynamics in physical systems. [ABSTRACT FROM AUTHOR]

p‐type 2D ferroelectric semiconductors (2D FeSs) play an increasingly essential role in the advanced nonvolatile and morphotropic beyond‐Moore electronic devices with high performance and low power consumption. But reliable p‐type 2D FeS with holes as majority carriers are still scarce. Herein, the first experimental realization of room‐temperature ferroelectricity in van der Waals layered β‐In1.75Sb0.25Se3 down to few layer is reported. The origin of ferroelectricity in β‐In1.75Sb0.25Se3 comes from aliovalent elemental substitution, antimony substituting to the indium sites (SbIn), changing the local environment of the central‐layer Se atoms. Thanks to the intrinsic ferroelectric and semiconducting natures, FeS field‐effect transistor (FeSFET) devices based on β‐In1.75Sb0.25Se3 exhibit reconfigurable, multilevel nonvolatile memory (NVM) states, which can be successively modulated by gate voltage stimuli. Furthermore, the inherent operation mechanism, due to the switchable polarization, indicates that a neuromorphic memory is also possible with 2D FeSFETs. These presented results facilitate the technological implementation of versatile 2D FeS devices for next‐generation logic‐in‐memory approach for Internet‐of‐Things entities. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Memristors are a candidate device for artificial neural systems due to their excellent conductance‐regulation ability and potential to simulate the characteristics of biological synapses. This study fabricated a Pt/TaOx/TiOy/Ti analog artificial synapse memristor that exhibits excellent multilevel storage property with a large on/off ratio of ≈660 times. The dynamic resistive switching mechanism is well expounded and validated by the reset stopping voltage dependent Schottky fitting results. Moreover, the essential biological synaptic characteristics such as long‐term potentiation/depression (LTP/D) and paired‐pulse facilitation (PPF) are successfully mimicked with a low pulse energy consumption of 12.69 nJ. A neuromorphic network constructed on the enhanced symmetry and linearity of conductance for this Pt/TaOx/TiOy/Ti memristive device can achieve 92.45% accuracy in recognizing handwritten pattern. These results demonstrate a significant potential for application Pt/TaOx/TiOy/Ti memristor in non‐volatile memory and bioinspired neuromorphic systems. [ABSTRACT FROM AUTHOR]

The development of neuromorphic devices is a pivotal step in the pursuit of low‐power artificial intelligence. A synaptic analog is one of the building blocks of this vision. The synaptic behavior of molecular La0.7Sr0.3MnO3/tris(8‐hydroxyquinolinato)gallium/AlOx/Co spintronic devices is studied, where the conductance plays the role of the synaptic weight. These devices are arranged in a crossbar configuration, the most effective architecture for the purpose. The conductance of each cross point is controlled separately by the application of voltage pulses: when set in the high conductance potentiated state, the devices show a spin‐valve magnetoresistance, while in the low conductance depressed state, no magnetoresistance is observed. The time dependence of the resistive switching behavior is an important parameter of the synaptic behavior and is very revealing of the underlying physical mechanisms. To study the time dynamics of the resistive switching after the voltage pulses, the response of the device to trains of potentiation and depression pulses, and the time‐resolved conductivity relaxation after the pulses are measured. The results are described with the conductivity model based on impurity energy levels in the organic semiconductor's gap. A flat distribution of the activation energies necessary to move these impurities is hypothesized, which can explain the observed glassy behavior. [ABSTRACT FROM AUTHOR]

Brain‐inspired parallel computing is increasingly considered a solution to overcome memory bottlenecks, driven by the surge in data volume. Extensive research has focused on developing memristor arrays, energy‐efficient computing strategies, and varied operational mechanisms for synaptic devices to enable this. However, to realize truly biologically plausible neuromorphic computing, it is essential to consider temporal and spatial aspects of input signals, particularly for systems based on the leaky integrate‐and‐fire model. This review highlights the significance of neuromorphic computing and outlines the fundamental components of hardware‐based neural networks. Traditionally, neuromorphic computing has relied on two‐terminal devices such as artificial synapses. However, these suffer from significant drawbacks, such as current leakage and the lack of a third terminal for precise synaptic weight adjustment. As alternatives, three‐terminal synaptic devices, including memtransistors, ferroelectric, floating‐gate, and charge‐trapped synaptic devices, as well as optoelectronic options, are explored. For an accurate replication of biological neural networks, it is vital to integrate artificial neurons and synapses, implement neurobiological functions in hardware, and develop sensory neuromorphic computing systems. This study delves into the operational mechanisms of these artificial components and discusses the integration process necessary for realizing biologically plausible neuromorphic computing, paving the way for future brain‐inspired electronic systems. [ABSTRACT FROM AUTHOR]

In order to fulfill the complex cognitive behaviors in neuromorphic systems with reduced peripheral circuits, the reliable electronic synapses mimicked by single device that achieves diverse long‐term and short‐term plasticity are essential. Phase change random access memory (PCRAM) is of great potential for artificial synapses, which faces, however, difficulty to realize short‐term plasticity due to the long‐lasting resistance drift. This work reports the ruthenium‐doped Ge2Sb2Te5 (RuGST) based PCRAM, demonstrating a series of synaptic behaviors of short‐term potentiation, pair‐pulse facilitation, long‐term depression, and short‐term plasticity in the same single device. The optimized RuGST electronic synapse with the high transformation temperature of hexagonal phase >380°C, the outstanding endurance >108 cycles, the low resistance drift factor of 0.092, as well as the extremely high linearity with correlation coefficients of 0.999 and 0.976 in parts of potentiation and depression. Further investigations also go insight to mechanisms of Ru doping according to thorough microstructure characterization, revealing that Ru dopant is able to enter GST lattices thus changing and stabilizing atomic arrangement of GST. This leads to the short‐term plasticity realized by RuGST PCRAM. Eventually, the proposed RuGST electronic synapses performs a high accuracy of ~94.1% in a task of image recognition of CIFAR‐100 database using ResNet 101. This work promotes the development of PCRAM platforms for large‐scale neuromorphic systems. [ABSTRACT FROM AUTHOR]

The unprecedented progress in artificial intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and processing in-memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the attention of the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. A future direction of the industry could be to implement state-of-the-art deep learning algorithms in emerging non-von Neumann computing paradigms for low-power computing on edge devices. [ABSTRACT FROM AUTHOR]

Silicon nitride (Si3N4) photonic integrated circuits (PICs) are of great interest due to their extremely low propagation loss and higher integration capabilities. The number of applications based on the silicon nitride integrated photonics platform continues to grow, including the Internet of Things (IoT), artificial intelligence (AI), light detection and ranging (LiDAR), hybrid neuromorphic and quantum computing. It's potential for CMOS compatibility, as well as advances in heterogeneous integration with silicon‐on‐insulator, indium phosphate, and lithium niobate on insulator platforms, are leading to an advanced hybrid large‐scale PICs. Here, they review key trends in Si3N4 photonic integrated circuit technology and fill an information gap in the field of state‐of‐the‐art devices operating from the visible to the mid‐infrared spectrum. A comprehensive overview of its microfabrication process details (deposition, lithography, etching, etc.) is introduced. Finally, the limitations and challenges of silicon nitride photonics performance are pointed out in an ultra‐wideband, providing routes and prospects for its future scaling and optimization. [ABSTRACT FROM AUTHOR]

Brain-inspired flexible neuromorphic devices are of great significance for next-generation high-efficiency wearable sensing and computing systems. In this paper, we propose a flexible organic electrochemical transistor using poly[(bithiophene)-alternate-(2,5-di(2-octyldodecyl)- 3,6-di(thienyl)-pyrrolyl pyrrolidone)] (DPPT-TT) as the organic semiconductor and poly(methyl methacrylate) (PMMA)/LiClO4 solid-state electrolyte as the gate dielectric layer. Under gate voltage modulation, an electric double layer (EDL) forms between the dielectric layer and the channel, allowing the device to operate at low voltages. Furthermore, by leveraging the double layer effect and electrochemical doping within the device, we successfully mimic various synaptic behaviors, including excitatory post-synaptic currents (EPSC), paired-pulse facilitation (PPF), high-pass filtering characteristics, transitions from short-term plasticity (STP) to long-term plasticity (LTP), and demonstrate its image recognition and storage capabilities in a 3 × 3 array. Importantly, the device's electrical performance remains stable even after bending, achieving ultra-low-power consumption of 2.08 fJ per synaptic event at −0.001 V. This research may contribute to the development of ultra-low-power neuromorphic computing, biomimetic robotics, and artificial intelligence. [ABSTRACT FROM AUTHOR]

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN--an analog electronic network made of selfadjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning. [ABSTRACT FROM AUTHOR]

In the strive for energy efficient computing, many different neuromorphic computing and engineering schemes have been introduced. Nanoparticle networks (NPNs) at the percolation threshold have been established as one of the promising candidates, e.g., for reservoir computing because among other useful properties they show self‐organization and brain‐like avalanche dynamics. The dynamic resistance changes trace back to spatio‐temporal reconfigurations in the connectivity upon resistive switching in distributed memristive nano‐junctions and nano‐gaps between neighboring nanoparticles. Until now, however, there has not yet been any direct imaging or monitoring of current paths in NPN. In this study, an NPN comprising of Ag/CxOyHz core/shell and Ag nanoparticles at the percolation threshold is reported. It is shown that this NPN is within a critical regime, exhibiting avalanche dynamics. To monitor in situ the evolving current paths in this NPN, active voltage contrast and resistive contrast imaging are used complementarily. Including simulations, the results provide experimental insight toward understanding the complex current response of the memristive NPN. As such, this study paves the way toward an experimental characterization of dynamic reorganizations in current paths inside NPN, which is highly relevant for validating and improving simulations and finally establishing a deeper understanding of switching dynamics in NPNs. [ABSTRACT FROM AUTHOR]

Highlights: A novel optoelectronic synapse compatible with existing chip technology is demonstrated. This device excels in mimicking memory and learning functions using light, making it ideal for future neuromorphic computing in biomedicine. Our design surpasses previous models with its ability to switch between short-term and long-term memory states using light pulses. Experiments on real-world biomedical data (electroencephalogram, electromyography, electrocardiogram) showed significant improvement in classification accuracy. This highlights the device's potential for advanced physiological signal processing and wearable health monitoring systems. The emergence of the Internet-of-Things is anticipated to create a vast market for what are known as smart edge devices, opening numerous opportunities across countless domains, including personalized healthcare and advanced robotics. Leveraging 3D integration, edge devices can achieve unprecedented miniaturization while simultaneously boosting processing power and minimizing energy consumption. Here, we demonstrate a back-end-of-line compatible optoelectronic synapse with a transfer learning method on health care applications, including electroencephalogram (EEG)-based seizure prediction, electromyography (EMG)-based gesture recognition, and electrocardiogram (ECG)-based arrhythmia detection. With experiments on three biomedical datasets, we observe the classification accuracy improvement for the pretrained model with 2.93% on EEG, 4.90% on ECG, and 7.92% on EMG, respectively. The optical programming property of the device enables an ultra-low power (2.8 × 10−13 J) fine-tuning process and offers solutions for patient-specific issues in edge computing scenarios. Moreover, the device exhibits impressive light-sensitive characteristics that enable a range of light-triggered synaptic functions, making it promising for neuromorphic vision application. To display the benefits of these intricate synaptic properties, a 5 × 5 optoelectronic synapse array is developed, effectively simulating human visual perception and memory functions. The proposed flexible optoelectronic synapse holds immense potential for advancing the fields of neuromorphic physiological signal processing and artificial visual systems in wearable applications. [ABSTRACT FROM AUTHOR]

Introduction: Great knowledge was gained about the computational substrate of the brain, but the way in which components and entities interact to perform information processing still remains a secret. Complex and large-scale network models have been developed to unveil processes at the ensemble level taking place over a large range of timescales. They challenge any kind of simulation platform, so that efficient implementations need to be developed that gain from focusing on a set of relevant models. With increasing network sizes imposed by these models, low latency inter-node communication becomes a critical aspect. This situation is even accentuated, if slow processes like learning should be covered, that require faster than real-time simulation. Methods: Therefore, this article presents two simulation frameworks, in which network-on-chip simulators are interfaced with the neuroscientific development environment NEST. This combination yields network traffic that is directly defined by the relevant neural network models and used to steer the network-on- chip simulations. As one of the outcomes, instructive statistics on network latencies are obtained. Since time stamps of different granularity are used by the simulators, a conversion is required that can be exploited to emulate an intended acceleration factor. Results: By application of the frameworks to scaled versions of the cortical microcircuit model--selected because of its unique properties as well as challenging demands--performance curves, latency, and traffic distributions could be determined. Discussion: The distinct characteristic of the second framework is its tree- based source-address driven multicast support, which, in connection with the torus topology, always led to the best results. Although currently biased by some inherent assumptions of the network-on-chip simulators, the results suit well to those of previous work dealing with node internals and suggesting accelerated simulations to be in reach. [ABSTRACT FROM AUTHOR]

Memristors, being prospective work‐horses of future electronics offer various types of memory (volatile and nonvolatile) along with specific computational functionalities. Further development of memristive technologies depends on the availability of suitable materials. These materials should be easily available, stable, and preferably of low toxicity. Commonly used materials are lead halide perovskites, however, they are highly toxic and unstable under ambient conditions. Therefore a novel material is developed on the basis of bismuth iodide. In reaction with butylammonium iodide, it yields a novel compound, butylammonium iodobismuthate (BABI). Here, a diffusive memristor is introduced based on this compound and evaluates its memristive and neuromorphic properties. In contrast to nonvolatile memristors, the BABI memristors exhibit diffusive dynamics, which enable them to store the information only for short periods of time. This property is utilized to mimic the short‐term synaptic plasticity described by the leaky integrate‐and‐fire model of a biological neuron. Combined with high switching uniformity and self‐rectifying behavior, these devices show high classification accuracy for MNIST handwritten datasets, paving the way for their application in neuromorphic computing systems. [ABSTRACT FROM AUTHOR]

Conducting polymers are proving to be useful for construction of resistive switching devices. This work reports the fabrication of a resistive switching device using Magnetite-Polyaniline (Fe3O4-PANI) nanocomposite. The device showed good non-volatile memory properties and can mimic neuromorphic synaptic behavior. Initially, Fe3O4 nanoparticles were synthesized using the co-precipitation method and PANI by oxidative polymerization and their nanocomposites of different compositions were prepared and fully characterized. The 10% Fe3O4-PANI-based RS device outperforms all others in terms of I–V switching performance. Furthermore, the optimized device (10% Fe3O4-PANI) has tuneable I–V characteristics. The device demonstrated excellent analog switching at ± 1.5 V and digital switching at ± 2.5 V. The memristive behavior of the Ag/10% Fe3O4-PANI/FTO device was confirmed by the pinched hysteresis loop in the I–V curves at different voltages, as well as the double-valued charged-flux characteristics. The device has good cycle-to-cycle reliability for switching voltages and switching currents, as demonstrated by the Weibull distribution and other statistical measures. Moreover, the device can retain memory states up to 6 × 103 s and shows a switching stability of 2 × 104 cycles. The device also showed linear potentiation and depression characteristics and mimicked excitatory post-synaptic current (EPSC) and paired-pulse facilitation (PPF) index properties similar to its biological counterpart. According to the charge transport model fitting results, the Ohmic and Child's square laws dominated in both analog and digital switching processes, and RS occurs due to the filamentary process. [ABSTRACT FROM AUTHOR]

We found that a second-order ideal memristor [whose state is the charge, i.e., x = q in v = R x , i , t i ] degenerates into a negative nonlinear resistor with an internal power source. After extending analytically and geographically the above local activity (experimentally verified by the two active higher-integral-order memristors extracted from the famous Hodgkin–Huxley circuit) to other higher-order circuit elements, we concluded that all higher-order passive memory circuit elements do not exist in nature and that the periodic table of the two-terminal passive ideal circuit elements can be dramatically reduced to a reduced table comprising only six passive elements: a resistor, inductor, capacitor, memristor, mem-inductor, and mem-capacitor. Such a bounded table answered an open question asked by Chua 40 years ago: Are there an infinite number of passive circuit elements in the world? [ABSTRACT FROM AUTHOR]

Neuromorphic computing has the potential to achieve the requirements of the next-generation artificial intelligence (AI) systems, due to its advantages of adaptive learning and parallel computing. Meanwhile, biocomputing has seen ongoing development with the rise of synthetic biology, becoming the driving force for new generation semiconductor synthetic biology (SemiSynBio) technologies. DNA-based biomolecules could potentially perform the functions of Boolean operators as logic gates and be used to construct artificial neural networks (ANNs), providing the possibility of executing neuromorphic computing at the molecular level. Herein, we briefly outline the principles of neuromorphic computing, describe the advances in DNA computing with a focus on synthetic neuromorphic computing, and summarize the major challenges and prospects for synthetic neuromorphic computing. We believe that constructing such synthetic neuromorphic circuits will be an important step toward realizing neuromorphic computing, which would be of widespread use in biocomputing, DNA storage, information security, and national defense.

Highlights A novel optoelectronic synapse compatible with existing chip technology is demonstrated. This device excels in mimicking memory and learning functions using light, making it ideal for future neuromorphic computing in biomedicine. Our design surpasses previous models with its ability to switch between short-term and long-term memory states using light pulses. Experiments on real-world biomedical data (electroencephalogram, electromyography, electrocardiogram) showed significant improvement in classification accuracy. This highlights the device's potential for advanced physiological signal processing and wearable health monitoring systems.

Recently, memristors have garnered widespread attention as neuromorphic devices that can simulate synaptic behavior, holding promise for future commercial applications in neuromorphic computing. In this paper, we present a memristor with an Au/Bi3.2La0.8Ti3O12 (BLTO)/ITO structure, demonstrating a switching ratio of nearly 103 over a duration of 104 s. It successfully simulates a range of synaptic behaviors, including long-term potentiation and depression, paired-pulse facilitation, spike-timing-dependent plasticity, spike-rate-dependent plasticity etc. Interestingly, we also employ it to simulate pain threshold, sensitization, and desensitization behaviors of pain-perceptual nociceptor (PPN). Lastly, by introducing memristor differential pairs (1T1R-1T1R), we train a neural network, effectively simplifying the learning process, reducing training time, and achieving a handwriting digit recognition accuracy of up to 97.19 %. Overall, the proposed device holds immense potential in the field of neuromorphic computing, offering possibilities for the next generation of high-performance neuromorphic computing chips.