Search

Steady-state visual evoked potentials (SSVEPs) are widely used for brain-computer interfaces (BCIs) as they provide a stable and efficient means to connect the computer to the brain with a simple flickering light. Previous studies focused on low-density frequency division multiplexing techniques, i.e. typically employing one or two light-modulation frequencies during a single flickering light stimulation. Here we show that it is possible to encode information in SSVEPs excited by high-density frequency division multiplexing, involving hundreds of frequencies. We then demonstrate the ability to transmit entire images from the computer to the brain/EEG read-out in relatively short times. High-density frequency multiplexing also allows to implement a photonic neural network utilizing SSVEPs, that is applied to simple classification tasks and exhibits promising scalability properties by connecting multiple brains in series. Our findings open up new possibilities for the field of neural interfaces, holding potential for various applications, including assistive technologies and cognitive enhancements, to further improve human-machine interactions. Steady state visually evoked potentials enable EEG vision-based brain computer interfaces. We show that it is possible to encode information distributed across 100+ frequencies. We encode images and perform simple physical computing classification tasks. Connecting more than one in brain in series improves the classification capability. [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]

A compact MOSFET-C floating/grounded meminductor emulator (MIE) model is presented for high operating frequency and low power operation. The proposed MIE uses only 22 MOSFETs and two capacitors. Its performance is theoretically analyzed and rigorously verified using the Cadence Virtuoso software and hardware prototypes. The proposed MIE operates appropriately for a wide range of frequencies up to 5 MHz with $590 \mu \text{W}$ power consumption at a 180nm CMOS technology node and manifests important signature properties. The MIE layout area in 180 nm CMOS technology is $13107.5 \mu \text{m}^{2}$. To analyze the effects of statistical variations in MIE elements, extensive Monte Carlo simulations have been performed to demonstrate the robustness of the proposed MIE. For experimental validation, hardware prototypes have been developed and tested successfully. An MIE-based adaptive learning neuromorphic circuit is presented to show that it can mimic the behavioral responses of amoeba under varying environments such as temperature. [ABSTRACT FROM AUTHOR]

The revolution in artificial intelligence (AI) brings up an enormous storage and data processing requirement. Large power consumption and hardware overhead have become the main challenges for building next-generation AI hardware. To mitigate this, neuromorphic computing has drawn immense attention due to its excellent capability for data processing with very low power consumption. While relentless research has been underway for years to minimize the power consumption in neuromorphic hardware, we are still a long way off from reaching the energy efficiency of the human brain. Furthermore, design complexity and process variation hinder the large-scale implementation of current neuromorphic platforms. Recently, the concept of implementing neuromorphic computing systems in cryogenic temperature has garnered intense interest thanks to their excellent speed and power metric. Several cryogenic devices can be engineered to work as neuromorphic primitives with ultra-low demand for power. Here, we comprehensively review the cryogenic neuromorphic hardware. We classify the existing cryogenic neuromorphic hardware into several hierarchical categories and sketch a comparative analysis based on key performance metrics. Our analysis concisely describes the operation of the associated circuit topology and outlines the advantages and challenges encountered by the state-of-the-art technology platforms. Finally, we provide insight to circumvent these challenges for the future progression of research. [ABSTRACT FROM AUTHOR]

Characterization and modeling of biological neural networks has emerged as a field driving significant advancements in our understanding of brain function and related pathologies. As of today, pharmacological treatments for neurological disorders remain limited, pushing the exploration of promising alternative approaches such as electroceutics. Recent research in bioelectronics and neuromorphic engineering have fostered the development of the new generation of neuroprostheses for brain repair. However, achieving their full potential necessitates a deeper understanding of biohybrid interaction. In this study, we present a novel real-time, biomimetic, cost-effective and user-friendly neural network capable of real-time emulation for biohybrid experiments. Our system facilitates the investigation and replication of biophysically detailed neural network dynamics while prioritizing cost-efficiency, flexibility and ease of use. We showcase the feasibility of conducting biohybrid experiments using standard biophysical interfaces and a variety of biological cells as well as real-time emulation of diverse network configurations. We envision our system as a crucial step towards the development of neuromorphic-based neuroprostheses for bioelectrical therapeutics, enabling seamless communication with biological networks on a comparable timescale. Its embedded real-time functionality enhances practicality and accessibility, amplifying its potential for real-world applications in biohybrid experiments. Beaubois et al. introduce a real-time biomimetic neural network for biohybrid experiments, providing a tool to study closed-loop applications for neuroscience and neuromorphic-based neuroprostheses. [ABSTRACT FROM AUTHOR]

The future computing beyond von Neumann era relies heavily on emerging devices that can extensively harness material and device physics to bring novel functionalities and can perform power-efficient and real time computing for artificial intelligence (AI) tasks. Additionally, brain-like computing demands large scale integration of synapses and neurons in practical circuits that requires the nanotechnology to support this hardware development, and all these should come at an affordable process complexity and cost to bring the solutions close to market rather soon. For bringing AI closer to quantum computing and space technologies, additional requirements are operation at cryogenic temperatures and radiation hardening. Considering all these requirements, nanoelectronic devices utilizing ferroic ordering has emerged as one promising alternative. The current review discusses the basic architectures of spintronic and ferroelectric devices for their integration in neuromorphic and analog memory applications, ferromagnetic and ferroelectric domain structures and control of their dynamics for reliable multibit memory operation, synaptic and neuronal leaky-integrate-and-fire (LIF) functions, concluding with their large-scale integration possibilities, challenges and future research directions. [ABSTRACT FROM AUTHOR]

For some years now, the locomotion mechanisms used by vertebrate animals have been a major inspiration for the improvement of robotic systems. These mechanisms range from adapting their movements to move through the environment to the ability to chase prey, all thanks to senses such as sight, hearing, and touch. Neuromorphic engineering is inspired by brain problem‐solving techniques with the goal of implementing models that take advantage of the characteristics of biological neural systems. While this is a well‐defined and explored area in this field, there is no previous work that fuses analog and neuromorphic sensors to control and modify robotic behavior in real time. Herein, a system is presented based on spiking neural networks implemented on the SpiNNaker hardware platform that receives information from both analog (force‐sensing resistor) and digital (neuromorphic retina) sensors and is able to adapt the speed and orientation of a hexapod robot depending on the stability of the terrain where it is located and the position of the target. These sensors are used to modify the behavior of different spiking central pattern generators, which in turn will adapt the speed and orientation of the robotic platform, all in real time. In particular, experiments show that the network is capable of correctly adapting to the stimuli received from the sensors, modifying the speed and heading of the robotic platform. [ABSTRACT FROM AUTHOR]

The brain's remarkable and efficient information processing capability is driving research into brain-inspired (neuromorphic) computing paradigms. Artificial aqueous ion channels are emerging as an exciting platform for neuromorphic computing, representing a departure from conventional solid-state devices by directly mimicking the brain's fluidic ion transport. Supported by a quantitative theoretical model, we present easy-to-fabricate tapered microchannels that embed a conducting network of fluidic nanochannels between a colloidal structure. Due to transient salt concentration polarization, our devices are volatile memristors (memory resistors) that are remarkably stable. The voltage-driven net salt flux and accumulation, that underpin the concentration polarization, surprisingly combine into a diffusionlike quadratic dependence of the memory retention time on the channel length, allowing channel design for a specific timescale. We implement our device as a synaptic element for neuromorphic reservoir computing. Individual channels distinguish various time series, that together represent (handwritten) numbers, for subsequent in silico classification with a simple readout function. Our results represent a significant step toward realizing the promise of fluidic ion channels as a platform to emulate the rich aqueous dynamics of the brain. [ABSTRACT FROM AUTHOR]

Neuromorphic engineering/computing addresses key challenges that modern electronics is facing such as high power consumption and high computing cost. Neuromorphic circuits for neurons and synapses will become key components to enable future neuromorphic computing system. Taking haptics for an example, in physical world, human haptic system is used to establish tactile sensation and feedback between human skin and physical objects. In Metaverse, computer haptics is used to build tactile sensation and haptic rendering when interacting with a virtual object and leads to an emerging technological field. This topic will be of great interest to thin film technology community and others to foster a discussion on possibility of using thin film devices to design such circuits for flexible and large area neuromorphic system. Author Keywords [ABSTRACT FROM AUTHOR]

Conventional computation techniques face challenges of deviations in Moore's law and the high‐power consumption of data‐centric computation tasks. Neuromorphic engineering attempts to overcome these issues by taking inspiration from neuron assemblies, ranging from distributed synaptic plasticity through orchestration of oscillator‐like action potential toward avalanche dynamics. Although solid networks of nanoparticles (NPs) are proven to replicate fingerprints of criticality and brain‐like dynamics, the aspect of dynamic spatial reconfigurations in the connectivity of networks remains unexplored. In this work, Ag/poly(ethylene glycol) (PEG) nanofluids are demonstrated as potential systems to mimic the spatio‐temporal reconfiguration of network connections. The nanofluids are prepared by directly loading Ag NPs from the gas aggregation cluster source into liquid PEG. The NPs exhibit a negative zeta potential in PEG; if the potential difference is applied between two electrodes submerged in this nanofluid, the NPs migrate toward the anode, accumulate in its vicinity, and form a conductive path. Spikes of electric current passing through the path are detected, accompanied by resistive switching phenomena, similar to the random switching dynamics in solid NPs networks. The unique behavior of Ag/PEG nanofluids makes them promising for the realization of spatio‐temporal reconfigurations in network topologies with the potential to transition to 3D. [ABSTRACT FROM AUTHOR]

Spiking neural network simulations are a central tool in Computational Neuroscience, Artificial Intelligence, and Neuromorphic Engineering research. A broad range of simulators and software frameworks for such simulations exist with different target application areas. Among these, PymoNNto is a recent Python-based toolbox for spiking neural network simulations that emphasizes the embedding of custom code in a modular and flexible way. While PymoNNto already supports GPU implementations, its backend relies on NumPy operations. Here we introduce PymoNNtorch, which is natively implemented with PyTorch while retaining PymoNNto's modular design. Furthermore, we demonstrate how changes to the implementations of common network operations in combination with PymoNNtorch's native GPU support can offer speed-up over conventional simulators like NEST, ANNarchy, and Brian 2 in certain situations. Overall, we show how PymoNNto's modular and flexible design in combination with PymoNNtorch's GPU acceleration and optimized indexing operations facilitate research and development of spiking neural networks in the Python programming language. [ABSTRACT FROM AUTHOR]

Imaging flow cytometry (IFC) is an advanced cell-analytic technology offering rich spatial information and fluorescence intensity for multi-parametric characterization. Manual gating in cytometry data enables the classification of discrete populations from the sample based on extracted features. However, this expert-driven technique can be subjective and laborious, often presenting challenges in reproducibility and being inherently limited to bivariate analysis. Numerous AI-driven cell classifications have recently emerged to automate the process of including multivariate data with enhanced reproducibility and accuracy. Our previous work demonstrated the early development of neuromorphic imaging cytometry, evaluating its feasibility in resolving conventional frame-based imaging systems' limitations in data redundancy, fluorescence sensitivity, and compromised throughput. Herein, we adopted a convolutional spiking neural network (SNN) combined with the YOLOv3 model (SNN-YOLO) to perform cell classification and detection on label-free samples under neuromorphic vision. Spiking techniques are inherently suitable post-processing techniques for neuromorphic vision sensing. The experiment was conducted with polystyrene-based microparticles, THP-1, and LL/2 cell lines. The network's performance was compared with that of a traditional YOLOv3 model fed with event-generated frame data to serve as a baseline. In this work, our SNN-YOLO outperformed the YOLOv3 baseline by achieving the highest average class accuracy of 0.974, compared to 0.962 for YOLOv3. Both models reported comparable performances across other key metrics and should be further explored for future auto-gating strategies and cytometry applications. [ABSTRACT FROM AUTHOR]

This work introduces on-device edge learning for cardiac abnormality detection by merging spiking 2D Convolutional Long-Short-Term Memory (ConvLSTM2D) with a bio-inspired shallow neural network, referred to as Closed-form Continuous-time (CfC), to form the sCCfC model. The model achieves an F1 score and AUROC of 0.82 and 0.91 in cardiac abnormalities detection. These results are comparable to the non-spiking ConvLSTM2D–CfC (ConvCfC) model [Huang et al., J. Cardiovasc. Transl. Res. (published online, 2024)]. Notably, the sCCfC model demonstrates a significantly higher energy efficiency with an estimated power consumption of 4.68 μJ/Inf (per inference) on an emulated Loihi's neuromorphic chip architecture, in contrast to ConvCfC model's consumption of 450 μJ/Inf on a conventional processor. In addition, as a proof-of-concept, we deployed the sCCfC model on the conventional and relatively resource-constrained Radxa Zero, which is equipped with an Amlogic S905Y2 processor for on-device training, which resulted in performance improvements. After initial training of two epochs on a conventional Graphics Processing Unit, the F1 score and AUROC improved from 0.46 and 0.65 to 0.56 and 0.73, respectively, with five additional epochs of on-device training. Furthermore, when presented with a new dataset, the sCCfC model showcases strong out-of-sample generalization capabilities that can constitute a pseudo-perspective test, achieving an F1 score and AUROC of 0.71 and 0.86, respectively. The spiking sCCfC also outperforms the non-spiking ConvCfC model in robustness regarding effectively handling missing electrocardiogram (ECG) channels during inference. The model's efficacy extends to single-lead ECG analysis, demonstrating reasonable accuracy in this context, while the focus of our work has been on the computational and memory complexities of the model. [ABSTRACT FROM AUTHOR]

Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies. [ABSTRACT FROM AUTHOR]

Human brains and bodies are not hardware running software: the hardware is the software. We reason that because the physics of artificial intelligence hardware and of human biological "hardware" is distinct, neuromorphic engineers need to be selective in the inspiration we take from neuroscience. Human brains and bodies are not hardware running software: the hardware is the software. Laydevan et al. reason that because the physics of artificial intelligence hardware and of human biological "hardware" is distinct, neuromorphic engineers need to be selective in the inspiration they take from neuroscience. [ABSTRACT FROM AUTHOR]

The neuromorphic computing architecture is a promising artificial intelligence for implementing hierarchical processing, in‐memory computing, event‐driven operation and functional specialization in computing systems. However, current investigations mainly focus on unisensory processing without objective experience which is contrary to the flexible sensory learning capability in the human brain that can sense and process information according to the ever‐changing environment. For example, a dominant paradigm for reconfigurable bio‐learning features is the emotional experience. The neurotransmitter dopamine is released during arousal, influencing the vital brain functions involved in cognition, reward learning, movement and motivation. Here, the on‐demand configuration of a biorealistic synaptic connection based on a 2D CaTa2O7 (CTO) device is demonstrated that can be adaptively reconfigured for a reinforcement learning purpose by the light‐active resistive switching, which originated from the photon‐regulated metaplasticity. The low energy consumption of 12.4 fJ endows the reinforcement learning system with high power efficiency and reliability. Finally, in‐sensor computing with a CTO synapse is implemented with a filtering function to process digital data in a neuromorphic engineering manner. This work demonstrates the feasibility of 2D perovskite neuromorphic device with enhanced biological plausibility in the approaching post‐Moore era. [ABSTRACT FROM AUTHOR]

Artificial vision is crucial for most artificial intelligence applications. Conventional artificial visual systems have been facing challenges in terms of real-time information processing due to the physical separation of sensors, memories, and processors, which results in the production of a large amount of redundant data as well as the data conversion and transfer between these three components consuming most of the time and energy. Emergent optoelectronic memristors with the ability to realize integrated sensing-computing-memory (ISCM) are key candidates for solving such challenges and therefore attract increasing attention. At present, the memristive ISCM devices can only perform primary-level computing with external light signals due to the fact that only monotonic increase of memconductance upon light irradiation is achieved in most of these devices. Here, we propose an all-optically controlled memristive ISCM device based on a simple structure of Au/ZnO/Pt with the ZnO thin film sputtered at pure Ar atmosphere. This device can perform advanced computing tasks such as nonvolatile neuromorphic computing and complete Boolean logic functions only by light irradiation, owing to its ability to reversibly tune the memconductance with light. Moreover, the device shows excellent operation stability ascribed to a purely electronic memconductance tuning mechanism. Hence, this study is an important step towards the next generation of artificial visual systems. [ABSTRACT FROM AUTHOR]

This document is an editorial published in the journal Frontiers in Neuroscience. It discusses the theoretical advances and practical applications of spiking neural networks (SNNs). The editorial highlights the growing popularity of neuromorphic engineering and the use of SNNs in various domains, such as image processing, biosignal analysis, activity recognition, and audio processing. The articles included in this special topic cover different applications and methodologies for training SNNs. The document emphasizes the wide potential of SNNs and encourages further research in this field, while also cautioning against misconceptions and the need to use SNNs appropriately for specific tasks. [Extracted from the article]

Oscillatory neural networks (ONNs) exhibit a high potential for energy-efficient computing. In ONNs, neurons are implemented with oscillators and synapses with resistive and/or capacitive coupling between pairs of oscillators. Computing is carried out on the basis of the rich, complex, non-linear synchronization dynamics of a system of coupled oscillators. The exploited synchronization phenomena in ONNs are an example of fully parallel collective computing. A fast system's convergence to stable states, which correspond to the desired processed information, enables an energy-efficient solution if small area and low-power oscillators are used, specifically when they are built on the basis of the hysteresis exhibited by phase-transition materials such as VO2. In recent years, there have been numerous studies on ONNs using VO2. Most of them report simulation results. Although in some cases experimental results are also shown, they do not implement the design techniques that other works on electrical simulations report that allow to improve the behavior of the ONNs. Experimental validation of these approaches is necessary. Therefore, in this study, we describe an ONN realized in a commercial CMOS technology in which the oscillators are built using a circuit that we have developed to emulate the VO2 device. The purpose is to be able to study in-depth the synchronization dynamics of relaxation oscillators similar to those that can be performed with VO2 devices. The fabricated circuit is very flexible. It allows programming the synapses to implement different ONNs, calibrating the frequency of the oscillators, or controlling their initialization. It uses differential oscillators and resistive synapses, equivalent to the use of memristors. In this article, the designed and fabricated circuits are described in detail, and experimental results are shown. Specifically, its satisfactory operation as an associative memory is demonstrated. The experiments carried out allow us to conclude that the ONN must be operated according to the type of computational task to be solved, and guidelines are extracted in this regard. [ABSTRACT FROM AUTHOR]

In this paper, we propose a compact and low-power mixed-signal approach to implementing convolutional operators that are often responsible for most of the chip area and power consumption of Convolutional Neural Network (CNN) processing chips. The convolutional operators consist of several multiply-and-accumulate (MAC) units. MAC units are the primary components that process convolutional layers and fully connected layers of CNN models. Analog implementation of MAC units opens a new paradigm for realizing low-power CNN processing chips, benefiting from less power and area consumption. The proposed mixed-signal convolutional operator comprises low-power binary-weighted current steering digital-to-analog conversion (DAC) circuits and accumulation capacitors. Compared with a conventional binary-weighted DAC, the proposed circuit benefits from optimum accuracy, smaller area, and lower power consumption due to its symmetric design. The proposed convolutional operator takes as input a set of 9-bit digital input feature data and weight parameters of the convolutional filter. It then calculates the convolutional filter's result and accumulates the resulting voltage on capacitors. In addition, the convolutional operator employs a novel charge-sharing technique to process negative MAC results. We propose an analog max-pooling circuit that instantly selects the maximum input voltage. To demonstrate the performance of the proposed mixed-signal convolutional operator, we implemented a CNN processing chip consisting of 3 analog convolutional operators, with each operator processing a 3 × 3 kernel. This chip contains 27 MAC circuits, an analog max-pooling, and an analog-to-digital conversion (ADC) circuit. The mixed-signal CNN processing chip is implemented using a CMOS 55 nm process, which occupies a silicon area of 0.0559 mm2 and consumes an average power of 540.6 μW. The proposed mixed-signal CNN processing chip offers an area reduction of 84.21% and an energy reduction of 91.85% compared with a conventional digital CNN processing chip. Moreover, another CNN processing chip is implemented with more analog convolutional operators to demonstrate the operation and structure of an example convolutional layer of a CNN model. Therefore, the proposed analog convolutional operator can be adapted in various CNN models as an alternative to digital counterparts. [ABSTRACT FROM AUTHOR]

Inspired by the principles of the biological nervous system, neuromorphic engineering has brought a promising alternative approach to intelligence computing with high energy efficiency and low consumption. As pivotal components of neuromorphic system, artificial spiking neurons are powerful information processing units and can achieve highly complex nonlinear computations. By leveraging the switching dynamic characteristics of memristive device, memristive neurons show rich spiking behaviors with simple circuit. This report reviews the memristive neurons and their applications in neuromorphic sensing and computing systems. The switching mechanisms that endow memristive devices with rich dynamics and nonlinearity are highlighted, and subsequently various nonlinear spiking neuron behaviors emulated in these memristive devices are reviewed. Then, recent development is introduced on neuromorphic system with memristive neurons for sensing and computing. Finally, we discuss challenges and outlooks of the memristive neurons toward high-performance neuromorphic hardware systems and provide an insightful perspective for the development of interactive neuromorphic electronic systems. [ABSTRACT FROM AUTHOR]

Networks of random-assembled gold clusters produced in the gas phase show resistive switching (RS) activity at room temperature and they are suitable for the fabrication of devices for neuromorphic data processing and classification. Fully connected cluster-assembled nanostructured Au films are characterized by a granular structure rich of interfaces, grain boundaries and crystalline defects. Here we report a systematic characterization of the electroforming process of the cluster-assembled films demonstrating how this process affects the interplay between the nano- and mesoscale film structure and the neuromorphic characteristics of the resistive switching activity. The understanding and the control of the influence of the resistive switching forming process on the organization of specific structures at different scales of the cluster-assembled films, provide the possibility to engineer random-assembled neuromorphic architectures for data processing task. [ABSTRACT FROM AUTHOR]

Research of artificial synapses is increasing in popularity with the development of bioelectronics and the appearance of wearable devices. Because the high-temperature treatment process of inorganic materialsis not compatible with flexible substrates, organic ferroelectric materials that are easier to process have emerged as alternatives. An organic synaptic device based on P(VDF-TrFE) was prepared in this study. The device showed reliable P/E endurance over 104 cycles and a data storage retention capability at 80 °C over 104 s. Simultaneously, it possessed excellent synaptic functions, including short-term/ long-term synaptic plasticity and spike-timing-dependent plasticity. In addition, the ferroelectric performance of the device remained stable even under bending (7 mm bending radius) or after 500 bending cycles. This work shows that low-temperature processed organic ferroelectric materials can provide new ideas for the future development of wearable electronics and flexible artificial synapses. [ABSTRACT FROM AUTHOR]

The brain has great capacity for computation and efficient resolution of complex problems, far surpassing modern computers. Neuromorphic engineering seeks to mimic the basic principles of the brain to develop systems capable of achieving such capabilities. In the neuromorphic field, navigation systems are of great interest due to their potential applicability to robotics, although these systems are still a challenge to be solved. This work proposes a spike‐based robotic navigation and environment pseudomapping system formed by a bioinspired hippocampal memory model connected to a posterior parietal cortex (PPC) model. The hippocampus is in charge of maintaining a representation of an environment state map, and the PPC is in charge of local decision‐making. This system is implemented on the SpiNNaker hardware platform using spiking neural networks. A set of real‐time experiments are applied to demonstrate the correct functioning of the system in virtual and physical environments on a robotic platform. The system is able to navigate through the environment to reach a goal position starting from an initial position, avoiding obstacles and mapping the environment. To the best of the authors' knowledge, this is the first implementation of an environment pseudomapping system with dynamic learning based on a bioinspired hippocampal memory. [ABSTRACT FROM AUTHOR]

The human brain possesses an exceptional information processing capability owing to the 3D and dense network architecture of numerous neurons and synapses. Brain‐inspired neuromorphic hardware can also benefit from 3D architectures, such as high integration of circuits and acquisition of highly complex dynamical systems. In this study, for future 3D neuromorphic engineering, 3D conductive polymer networks consisting of poly(3,4‐ethylenedioxy‐thiophene) doped with poly(styrene sulfonate) anions (PEDOT:PSS) are successfully and stably fabricated between multiple electrodes from scratch in precursor solution by electropolymerization. The networks efficiently emulate the 3D local connections between neighboring neurons observed in the cortex. This novel technology, which allows 3D conductive wiring only between desired electrodes, is unprecedented and has potential as an underlying technology for 3D integration. Furthermore, the experimental results also conclusively prove that conductance modification can be performed by manipulating the physical and chemical properties of 3D branch‐wired conductive polymer wires, thus demonstrating for the first time the feasibility of neuromorphic wetware with enhanced biological plausibility in the subsequent post‐Moore era. [ABSTRACT FROM AUTHOR]

This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain's structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behaviors similar to the human brain. Compared to conventional architectures using a simplified leaky integrate-and-fire (LIF) neuron model, TOM showcases robust performance, even in noisy conditions. TOM's adaptability and unique organizational structure, rooted in the Columnar-Organized Memory (COM) framework, position it as a transformative digital memory processing solution. Innovative neural architecture, advanced recognition mechanisms, and integration of synaptic plasticity rules enhance TOM's cognitive capabilities. We have compared the TOM architecture with a conventional floating-point architecture, using a simplified LIF neuron model. We also implemented tests with varying noise levels and partially erased messages to evaluate its robustness. Despite the slight degradation in performance with noisy messages beyond 30%, the TOM architecture exhibited appreciable performance under less-than-ideal conditions. This exploration into the TOM architecture reveals its potential as a framework for future neuromorphic systems. This study lays the groundwork for future applications in implementing neuromorphic chips for high-performance intelligent edge devices, thereby revolutionizing industries and enhancing user experiences within the power of artificial intelligence. [ABSTRACT FROM AUTHOR]

Humanity is spurred to tackle multi-sectorial global challenges involving everyone on Earth. Global challenges require global agendas to be faced. Global plans focus on the management of Complex Systems. Therefore, the development of Complexity Science is urgent. This contribution outlines the investigation of Complex Systems from an ontological and epistemological point of view. It highlights the relevant role of Natural Computing in facing the description, prediction, and more in-depth comprehension of Complex Systems. Its rationale constitutes an interpretative key for describing and understanding the behaviour of Complex Systems. Furthermore, developing new algorithms and possibly new computing machines will allow humanity to tackle Epistemological Complexity more effectively. Among all the possible sources of inspiration, human intelligence is undoubtedly the most in vogue. This work reveals that the imitation of human intelligence and the consequent development of Artificial Intelligence can be carried out not only through traditional strategies but also through Molecular, Supramolecular, and Systems Chemistries. Chemical Artificial Intelligence promises to contribute to understanding the ontology of Complex Systems and facing epistemological Complexity. [ABSTRACT FROM AUTHOR]

This document is a technical perspective on research related to general-purpose brain-inspired computing systems. The field of brain-inspired computing, also known as neuromorphic computing, aims to utilize mechanisms present in the brain to improve performance in artificial intelligence and computing. The research community in this field has seen contributions from academic and industrial players, but neuromorphic systems have yet to make significant progress in the AI hardware market. One challenge is that these systems often require new design approaches and specialized knowledge, making it difficult for non-experts to achieve maximum performance. The document highlights the work of the CRAFT group and the Center for Brain-Inspired Computing Research at Tsinghua University, which has developed a holistic research outlook to address these challenges. Their work includes the development of hybrid models that bridge artificial and spiking neurons, the exploration of bio-inspired learning mechanisms, and the design of compilers for domain-specific architectures. The document concludes that while there is still progress to be made, this research provides a methodical and principled direction for the development of neuromorphic systems, improving accessibility and accelerating progress towards artificial general intelligence. [Extracted from the article]

The 6th volume of Advanced Intelligent Systems (AIS) has been successful in establishing itself as a reputable journal for research on topics such as robotics, artificial intelligence, and machine learning. The journal has achieved a high impact factor and has published highly cited articles. AIS promotes open communication and inclusivity, and its articles have gained attention on social media and news outlets. The journal also organizes events and publishes special issues on various interdisciplinary topics. AIS continues to innovate by publishing interactive content and developing submission checklists to standardize data reporting. The editors express gratitude to authors, reviewers, and the Editorial Advisory Board for their support. [Extracted from the article]

Oscillatory neural networks (ONNs) exhibit a high potential for energy-efficient computing. In ONNs, neurons are implemented with oscillators and synapses with resistive and/or capacitive coupling between pairs of oscillators. Computing is carried out on the basis of the rich, complex, non-linear synchronization dynamics of a system of coupled oscillators. The exploited synchronization phenomena in ONNs are an example of fully parallel collective computing. A fast system’s convergence to stable states, which correspond to the desired processed information, enables an energy-efficient solution if small area and low-power oscillators are used, specifically when they are built on the basis of the hysteresis exhibited by phase-transition materials such as VO2. In recent years, there have been numerous studies on ONNs using VO2. Most of them report simulation results. Although in some cases experimental results are also shown, they do not implement the design techniques that other works on electrical simulations report that allow to improve the behavior of the ONNs. Experimental validation of these approaches is necessary. Therefore, in this study, we describe an ONN realized in a commercial CMOS technology in which the oscillators are built using a circuit that we have developed to emulate the VO2 device. The purpose is to be able to study in-depth the synchronization dynamics of relaxation oscillators similar to those that can be performed with VO2 devices. The fabricated circuit is very flexible. It allows programming the synapses to implement different ONNs, calibrating the frequency of the oscillators, or controlling their initialization. It uses differential oscillators and resistive synapses, equivalent to the use of memristors. In this article, the designed and fabricated circuits are described in detail, and experimental results are shown. Specifically, its satisfactory operation as an associative memory is demonstrated. The experiments carried out allow us to conclude that the ONN must be operated according to the type of computational task to be solved, and guidelines are extracted in this regard.

Memristive devices have shown a great potential for non-volatile memory circuits and neuromorphic computing. For both applications it is essential to know the physical mechanisms behind resistive switching; in particular, the time response to external voltage signals. To shed light in these issues we have studied the role played by the applied voltage ramp rate in the electrical properties of TiN/Ti/HfO2/W metal–insulator–metal resistive switching devices. Using an ad hoc experimental set-up, the current–voltage characteristics were measured for ramp rates ranging from 100 mV s−1–1 MV s−1. These measurements were used to investigate in detail the set and reset transitions. It is shown that the highest ramp rates allow controlling the resistance values corresponding to the intermediate states at the very beginning of the reset process, which is not possible by means of standard quasistatic techniques. Both the set and reset voltages increase with the ramp rate because the oxygen vacancies movement is frequency dependent so that, when the ramp rate is high enough, the conductive filaments neither fully form nor dissolve. In agreement with Chua's theory of memristive devices, this effect causes the device resistance window to decrease as the ramp rate increases, and even to vanish for very high ramp rates. Remarkably, we demonstrate that the voltage ramp rate can be straightforwardly used to control the conductance change of the switching devices, which opens up a new way to program the synaptic weights when using these devices to mimic synapses for neuromorphic engineering applications. Moreover, the data obtained have been compared with the predictions of the dynamic memdiode model. [ABSTRACT FROM AUTHOR]

We examine the challenging "marriage" between computational efficiency and biological plausibility—A crucial node in the domain of spiking neural networks at the intersection of neuroscience, artificial intelligence, and robotics. Through a transdisciplinary review, we retrace the historical and most recent constraining influences that these parallel fields have exerted on descriptive analysis of the brain, construction of predictive brain models, and ultimately, the embodiment of neural networks in an enacted robotic agent. We study models of Spiking Neural Networks (SNN) as the central means enabling autonomous and intelligent behaviors in biological systems. We then provide a critical comparison of the available hardware and software to emulate SNNs for investigating biological entities and their application on artificial systems. Neuromorphics is identified as a promising tool to embody SNNs in real physical systems and different neuromorphic chips are compared. The concepts required for describing SNNs are dissected and contextualized in the new no man's land between cognitive neuroscience and artificial intelligence. Although there are recent reviews on the application of neuromorphic computing in various modules of the guidance, navigation, and control of robotic systems, the focus of this paper is more on closing the cognition loop in SNN-embodied robotics. We argue that biologically viable spiking neuronal models used for electroencephalogram signals are excellent candidates for furthering our knowledge of the explainability of SNNs. We complete our survey by reviewing different robotic modules that can benefit from neuromorphic hardware, e.g., perception (with a focus on vision), localization, and cognition. We conclude that the tradeoff between symbolic computational power and biological plausibility of hardware can be best addressed by neuromorphics, whose presence in neurorobotics provides an accountable empirical testbench for investigating synthetic and natural embodied cognition. We argue this is where both theoretical and empirical future work should converge in multidisciplinary efforts involving neuroscience, artificial intelligence, and robotics. [ABSTRACT FROM AUTHOR]

Spike-based perception brings up a new research idea in the field of neuromorphic engineering. A high-performance biologically inspired flexible spiking neural network (SNN) architecture provides a novel method for the exploration of perception mechanisms and the development of neuromorphic computing systems. In this article, we present a biological-inspired spike-based SNN perception digital system that can realize robust perception. The system employs a fully paralleled pipeline scheme to improve the performance and accelerate the processing of feature extraction. An auditory perception system prototype is realized on ten Intel Cyclone field-programmable gate arrays, which can reach the maximum frequency of 107.28 MHz and the maximum throughput of 5364 Mbps. Our design also achieves the power of 5. 148 W/system and energy efficiency of 845.85 μ J. Our auditory perception implementation is also proved to have superior robustness compared with other SNN systems. We use TIMIT digit speech in noise in accuracy testing. Result shows that it achieves up to 85.75% speech recognition accuracy under obvious noise conditions (signal-to-noise ratio of 20 dB) and maintain small accuracy attenuation with the decline of the signal-to-noise ratio. The overall performance of our proposed system outperforms the state-of-the-art perception system on SNN. [ABSTRACT FROM AUTHOR]

Since HfOx‐based ferroelectric tunnel junctions (FTJs) are attractive compared to perovskite‐based FTJs and other emerging memory devices, they are being actively studied recently. They have advantages such as a simple metal–insulator–metal structure, complementary metal oxide semiconductor (CMOS) compatibility, non‐destructive operation, and low power consumption. Moreover, doped HfOx‐based FTJs are in the spotlight in terms of neuromorphic engineering as a way of advancing from the von Neumann structure. In particular, Al dopant is effective for inducing ferroelectric properties due to its smaller radius than that of Hf. The optimal concentration of Al varies depending on the device materials and the annealing conditions during deposition. Therefore, in‐depth research is required for neuromorphic applications. Herein, the properties of FTJ devices according to Al doping concentrations are analyzed. Subsequently, using the device with the highest remanent polarization, neuromorphic applications are implemented, including spike‐timing‐dependent plasticity (STDP), paired‐pulse facilitation (PPF), long‐term potentiation, and depression. The characteristics in different frequency regions are also studied to satisfy the demand for fast switching. Finally, the FTJ device is used as a physical reservoir in reservoir computing for efficient processing of time‐dependent inputs. [ABSTRACT FROM AUTHOR]

The potential role of bottom-up Synthetic Cells (SCs) in the Internet of Bio-Nano Things (IoBNT) is discussed. In particular, this perspective paper focuses on the growing interest in networks of biological and/or artificial objects at the micro- and nanoscale (cells and subcellular parts, microelectrodes, microvessels, etc.), whereby communication takes place in an unconventional manner, i.e., via chemical signaling. The resulting "molecular communication" (MC) scenario paves the way to the development of innovative technologies that have the potential to impact biotechnology, nanomedicine, and related fields. The scenario that relies on the interconnection of natural and artificial entities is briefly introduced, highlighting how Synthetic Biology (SB) plays a central role. SB allows the construction of various types of SCs that can be designed, tailored, and programmed according to specific predefined requirements. In particular, "bottom-up" SCs are briefly described by commenting on the principles of their design and fabrication and their features (in particular, the capacity to exchange chemicals with other SCs or with natural biological cells). Although bottom-up SCs still have low complexity and thus basic functionalities, here, we introduce their potential role in the IoBNT. This perspective paper aims to stimulate interest in and discussion on the presented topics. The article also includes commentaries on MC, semantic information, minimal cognition, wetware neuromorphic engineering, and chemical social robotics, with the specific potential they can bring to the IoBNT. [ABSTRACT FROM AUTHOR]

We propose a new model for a neuromorphic olfactory analyzer based on memristive synapses. The model comprises a layer of receptive neurons that perceive various odors and a layer of "decoder" neurons that recognize these odors. It is demonstrated that connecting these layers with memristive synapses enables the training of the "decoder" layer to recognize two types of odorants of varying concentrations. In the absence of such synapses, the layer of "decoder" neurons does not exhibit specificity in recognizing odorants. The recognition of the 'odorant' occurs through the neural activity of a group of decoder neurons that have acquired specificity for the odorant in the learning process. The proposed phenomenological model showcases the potential use of a memristive synapse in practical odorant recognition applications. [ABSTRACT FROM AUTHOR]

Atomic cluster-based networks represent a promising architecture for the realization of neuromorphic computing systems, which may overcome some of the limitations of the current computing paradigm. The formation and breakage of links between the clusters are of utmost importance for the functioning of these computing systems. This paper reports the results of molecular dynamics simulations of synapse (bridge) formation at elevated temperature and thermal breaking processes between 2.8 nm-sized Au1415 clusters deposited on a carbon substrate, a model system. Crucially, we find that the bridge formation process is driven by the diffusion of gold atoms along the substrate, no matter how small the gap between the clusters themselves. The complementary simulations of the bridge breaking process reveal the existence of a threshold bias voltage to activate bridge rupture via Joule heating. These results provide an atomistic-level understanding of the fundamental dynamical processes occurring in neuromorphic cluster arrays. [ABSTRACT FROM AUTHOR]

Mutual interactions between humans and devices are being widely adopted, including wearable electromechanical devices known as robotic exoskeletons. Among various modules used to control the human-robot interactions, compliance control (CC) is needed to ensure human safety and avoid abnormal operations. Here we propose a novel CC system with co-integrated neuromorphic devices composed of a pre-synapse, an interneuron, and a post-synapse. These devices are the same homotypic MOSFET with a SONOS configuration, despite having different functions. For proof-of-concept, semi-empirical simulations were conducted with the aid of an LTspice simulator, by reflecting measured neuron and synapse characteristics from the fabricated tri-gate FinFETs. The extremely low-power consumption of 0.2 mW, which is 55-fold smaller than other conventional approaches, was achieved. A high response rate of up to 3 ms was attained as well. Moreover, by automatically adjusting output signal frequency and amplitude, the micro-sized neuromorphic CC system can avoid excess actuator motion in human-robot interactions. [ABSTRACT FROM AUTHOR]

Neuromorphic computing has emerged as a better alternative for developing next-generation artificial intelligent systems. Resistive Random Access Memory (RRAM) have been widely explored to represent the synaptic weights in artificial neural networks. Despite significant advances in device technology, precise modulation of conductance required for maintaining high accuracy remains a challenge. These devices suffer mainly from Cycle-to-Cycle and Device-to-Device variations, which make it even more difficult to implement reliable neuromorphic systems. To address these issues, we propose an RRAM-based synaptic architecture with continuous sensing and feedback scheme to stop RRAM programming when the required conductance is achieved. The weight change mechanism is incorporated in the proposed architecture enabling it to be used for on-chip training. Unlike contemporary architectures, which require a precise gap between different resistive states, the proposed feedback scheme to stop RESET operation provides flexibility in choosing resistive states. Thus, employing the proposed architecture, 4-bits/cell can be programmed simultaneously, which is at par with the existing start-of-the-art designs. The proposed architecture is tolerant to 22% variation in RRAM resistance. The minimal resistance margin between two resistive states is $4\ K\Omega$ , with an average energy consumption of $0.1\ pJ/cell$ and an average latency of $1.07\, \mu s$. [ABSTRACT FROM AUTHOR]

In this article, we have proposed a novel reconfigurable synaptic and neuronal transistor (RSNT) at sub-10 nm regime for the spiking neural network (SNN). From calibrated TCAD simulations, we demonstrated that the proposed RSNT mimics both synaptic and neuronal functionalities. The proposed RSNT comprises of two gates, front gate (FG) and back gate (BG) to configure as a synapse and neuron, respectively. We investigated the synapse characteristics such as short-term (ST) and long-term (LT) synaptic plasticity (STSP/LTSP). The STSP is distinguished in terms of short-term potentiation/depression and paired-pulse facilitation/depression (PPF/PPD). And the LTSP is characterized by analyzing the long-term potentiation/depression (LTP/LTD) and spike-timing-dependent plasticity (STDP). Moreover, the energy consumption of the RSNT device during the facilitation and depression events is 4.5 pJ and 6.0 pJ, respectively. The reconfigurable leaky integrate-and-fire (LIF) neuron requires 1.2 fJ energy per spike (E $_{spike}$) for firing which is $\sim$ 10 $^{4}$ × less E $_{spike}$ and $\sim$ 9 × lower supply voltage as compared to the PD-SOI MOSFET based LIF neuron. The simulation results assures that the proposed RSNT with various synaptic and LIF neuronal characteristics at sub-10 nm regime has potential application for the neuromorphic systems as it increases the integration density and eases the fabrication complexity. [ABSTRACT FROM AUTHOR]

Lithium (Li)-ion materials such as LiCoO2 and (Li3PO4)-N (LiPON) are used in Li-ion all-solid-state batteries, and are now expected to be used as ion-electron hybrid materials to create a new degree of freedom in future integrated circuits. We fabricated thin-film devices on the basis of LiCoO2/LiPON/Cu and ultrathin titanium oxide ( ${\mathrm {TiO}}_{x}$ ) to demonstrate their new type of resistance change mechanism and characteristics. Multi-level resistance changes promising as synaptic plasticity were obtained, and the resistance properties enable neuromorphic computing to enter a new era.

We present the Surrogate-gradient Online Error-triggered Learning (SOEL)system for online few-shot learning on neuromorphic processors. The SOELlearning system uses a combination of transfer learning and principles ofcomputational neuroscience and deep learning. We show that partially traineddeep Spiking Neural Networks (SNNs) implemented on neuromorphic hardware canrapidly adapt online to new classes of data within a domain. SOEL updatestrigger when an error occurs, enabling faster learning with fewer updates.Using gesture recognition as a case study, we show SOEL can be used for onlinefew-shot learning of new classes of pre-recorded gesture data and rapid onlinelearning of new gestures from data streamed live from a Dynamic Active-pixelVision Sensor to an Intel Loihi neuromorphic research processor.

Computing and neuromorphic engineering areas have gained notoriety over the past few years. The current paradigm of computing, based on a centralized system, is an obstacle to evolution. It is necessary to leave Von Neumann's paradigm behind and invest in a more organic and decentralized model of technology. Neuromorphic computers are not made with transistors, but with memristors, electronic components are capable of retaining memory. In this study, the aim is to analyze the behavior of a memristor based on graphene oxide (GO) doped with silver simulating the neuronal membrane and validate the operation of the resistor–capacitor (RC) circuit as a possible tool for analysis of memristor devices. Electrical analyses are carried out in two stages: first, an I × V analysis of device parameters is carried out with a picoammeter; then, a test with a developed RC circuit is carried out in three conditions: a simulated RC circuit, an experimental analysis of the same circuit, and finally, the RC circuit is associated with the memristor. Memristor device presents threshold switching, which is a desirable feature when it is required to simulate neuronal firing. In addition, when associated with the RC circuit, the curve behavior obtained for charging and discharging the capacitor becomes nonlinear. [ABSTRACT FROM AUTHOR]

Reservoir computing systems are promising for application in bio-inspired neuromorphic networks as they allow the considerable reduction of training energy and time costs as well as an overall system complexity. Conductive three-dimensional structures with the ability of reversible resistive switching are intensively developed to be applied in such systems. Nonwoven conductive materials, due to their stochasticity, flexibility and possibility of large-scale production, seem promising for this task. In this work, fabrication of a conductive 3D material by polyaniline synthesis on a polyamide-6 nonwoven matrix was shown. An organic stochastic device with a prospective to be used in reservoir computing systems with multiple inputs was created based on this material. The device demonstrates different responses (output current) when different combinations of voltage pulses are applied to the inputs. The approach is tested in handwritten digit image classification task in simulation with the overall accuracy exceeding 96%. This approach is beneficial for processing multiple data flows within a single reservoir device. [ABSTRACT FROM AUTHOR]

Circuit implementation of the mathematical model of neurons represents an alternative approach for the validation of their dynamical behaviors for their potential applications in neuromorphic engineering. In this work, an improved FitzHugh–Rinzel neuron, in which the traditional cubic nonlinearity is swapped with a sine hyperbolic function, is introduced. This model has the advantage that it is multiplier-less since the nonlinear component is just implemented with two diodes in anti-parallel. The stability of the proposed model revealed that it has both stable and unstable nodes around its fixed points. Based on the Helmholtz theorem, a Hamilton function that enables the estimation of the energy released during the various modes of electrical activity is derived. Furthermore, numerical computation of the dynamic behavior of the model revealed that it was able to experience coherent and incoherent states involving both bursting and spiking. In addition, the simultaneous appearance of two different types of electric activity for the same neuron parameters is also recorded by just varying the initial states of the proposed model. Finally, the obtained results are validated using the designed electronic neural circuit, which has been analyzed in the Pspice simulation environment. [ABSTRACT FROM AUTHOR]

The essential step for developing neuromorphic systems is to construct more biorealistic elementary devices with rich spatiotemporal dynamics to exhibit highly separable responses in dynamic environmental circumstances. Unlike transistor‐based devices and circuits with zeroth‐order complexity, memristors intrinsically express some simple biomimetic functions. However, with only two‐terminal structure, precise control of operation principles to ensure large dynamic space, improved linearity and symmetry, multimodal operation as well as high‐order complexity is hard to achieve in a traditional memristor owing to its limited degree of freedom. Therefore, multiterminal memristors including both concrete terminals and virtual terminals (light, pressure, gas, ferroelectric polarity, etc.) have been proposed to obtain precise modulation of memristive characteristics. This review focuses on the recent progress in multiterminal memristors and their neuromorphic applications. The operation principle, application of multiterminal memristor on neuromorphic computing in different scenarios, existing challenges and future prospects are discussed. [ABSTRACT FROM AUTHOR]