Search

The organic evidence from neuroscience proves that precise spike times are used for information exchange between two biological neurons rather than the firing rates. One of the prominent reasons, along with energy and computational efficiency, is that spiking neural networks (SNNs) are getting more attention nowadays. The spiking neurons in SNN mimic the biological neuron more than its predecessors. Despite the few efficient supervised learning algorithms for SNN, only some investigated the biological properties such as axonal noise, random synaptic delays, spontaneous spike-firing, and random switching of the gamma-aminobutyric acid (GABA)-switch. The aforementioned properties are essential for making spiking neurons more biologically realistic, which is one of the major strengths of SNN. The GABA switch decides the most crucial activity, whether a neuron will be excitatory or inhibitory. This paper proposes a novel and efficient approach to handle non-linear patterns using a single leaky-integrate-and-fire (LIF) spiking neuron connected with many noisy synapses with random synaptic delays. In addition, the spontaneous firing of a neuron and random switching of signs in synaptic weights having equal probability akin to GABA-switch are efficiently implemented. Moreover, a hybrid kernel is proposed as the synapse model to cope with the noise properly, which makes the synapse model more efficient. The error-tuning is carried out using the elitist floating-point genetic algorithm. Four datasets were used for benchmarking, and experimentally, better results were obtained than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The Lobular Giant Motion Detector (LGMD) is a neuron in the insect visual system that has been extensively studied, especially in locusts. This neuron is highly sensitive to rapidly approaching objects, allowing insects to react quickly to avoid potential threats such as approaching predators or obstacles. In the realm of intelligent vehicles, due to the lack of performance of conventional RGB cameras in extreme light conditions or at high-speed movements. Inspired by biological mechanisms, we have developed a novel neuromorphic dynamic vision sensor (DVS) driven LGMD spiking neural network (SNN) model. SNNs, distinguished by their bio-inspired spiking dynamics, offer a unique advantage in processing time-varying visual data, particularly in scenarios where rapid response and energy efficiency are paramount. Our model incorporates two distinct types of Leaky Integrate-and-Fire (LIF) neuron models and synapse models, which have been instrumental in reducing network latency and enhancing the system's reaction speed. And addressing the challenge of noise in event streams, we have implemented denoising techniques to ensure the integrity of the input data. Integrating the proposed methods, ultimately, the model was integrated into an intelligent vehicle to conduct real-time obstacle avoidance testing in response to looming objects in simulated real scenarios. The experimental results show that the model's ability to compensate for the limitations of traditional RGB cameras in detecting looming targets in the dark, and can detect looming targets and implement effective obstacle avoidance in complex and diverse dark environments. [ABSTRACT FROM AUTHOR]

In this paper, a comprehensive exploration is undertaken to elucidate the utilization of Spiking Neural Networks (SNNs) within the biomedical domain. The investigation delves into the experimentally validated advantages of SNNs in comparison to alternative models like LSTM, while also critically examining the inherent limitations of SNN classifiers or algorithms. SNNs exhibit distinctive advantages that render them particularly apt for targeted applications within the biomedical field. Over time, SNNs have undergone extensive scrutiny in realms such as neuromorphic processing, Brain-Computer Interfaces (BCIs), and Disease Diagnosis. Notably, SNNs demonstrate a remarkable affinity for the processing and analysis of biomedical signals, including but not limited to electroencephalogram (EEG), electromyography (EMG), and electrocardiogram (ECG) data. This paper initiates its exploration by introducing some of the biomedical applications of EMG, such as the classification of hand gestures and motion decoding. Subsequently, the focus extends to the applications of SNNs in the analysis of EEG and ECG signals. Moreover, the paper delves into the diverse applications of SNNs in specific anatomical regions, such as the eyes and noses. In the final sections, the paper culminates with a comprehensive analysis of the field, offering insights into the advantages, disadvantages, challenges, and opportunities introduced by various SNN models in the realm of healthcare and biomedical domains. This holistic examination provides a nuanced perspective on the potential transformative impact of SNN across a spectrum of applications within the biomedical landscape. [ABSTRACT FROM AUTHOR]

Paraneoplastic neurologic syndromes are cancer-associated, immune-mediated neurologic manifestations that may involve any part of the nervous system. They usually present with characteristic neurologic features and should be considered in high-risk phenotypes such as limbic encephalitis, encephalomyelitis, rapidly progressive cerebellar syndrome, opsoclonus–myoclonus, sensory neuronopathy, enteric neuropathy, and Lambert–Eaton myasthenic syndrome. The diagnosis is made by antibody positivity in the serum or cerebrospinal fluid, in the presence of an appropriate clinical phenotype. Findings on antibody testing by immunoblot should always be verified by immunofluorescence. We report a rare case of sensory neuronopathy with triple paraneoplastic antibody positivity (anti-Hu, anti-collapsing response-mediator protein 5, and anti-amphiphysin) on immunoblot but only anti-Hu positivity on immunofluorescence. The presence of lower facial dyskinesias should raise the possibility of an immune-mediated neurologic syndrome in the appropriate clinical context.

In this paper, a single SiGe Tunnel FET is used to design a Leaky Integrate and Fire (LIF) neuron with significant improvement in area, energy and cost. SiGe Tunnel Field-Effect Transistor (FET) transfer characteristic with steep sub-threshold swing has been used to observe LIF neuronal characteristics. By employing calibrated simulation using Atlas 2D, we have verified that the TFET with LIF characteristics can effectively replicate neuron behavior without relying on external circuitry. The proposed LIF neuron, based on SiGe TFET, exhibits significantly reduced energy consumption, specifically 210 fJ per spike. This energy consumption is ≈ 215 times lower compared to previously reported single-device neurons in existing literature. Additionally, we have achieved an impressive recognition precision of 91.3 % for Modified National Institute of Standards and Technology (MNIST) images. [ABSTRACT FROM AUTHOR]

The use of neural modeling tools is becoming increasingly common in the exploration of human brain behavior, enabling effective simulations through event-driven methodologies. As a result, years of study and advancements in the field of neurotechnology have led to the creation of several artificial neural network approaches that mimic biological neural networks. The event-driven approach provides an effective method for mimicking large-scale spiking neural networks (SNNs), by taking advantage of the brain's sparse processing. This paper investigates SNN employing a leaky integrate-and-fire neuron model with latency estimation through FNS. A three-layer feedforward network (FFN) is constructed, incorporating design parameters from Config Wizard. Notably, our study sheds light on the impact of synchrony within a simple FFN. Through the incorporation of biologically plausible delay effects, our model offers novel insights that complement the existing literature. Neural activity is organized in CSV format files, facilitating the reconstruction of electrophysiological-like signals. FNS enables a comprehensive exploration of interactions within and between populations of spiking neurons. In the near future, we intend to use these findings in situations where this particular class of neural networks and digital signal processing (DSP) applications can be combined to create potent nonlinear DSP techniques. [ABSTRACT FROM AUTHOR]

Neuromorphic devices capable of training spiking neural networks (SNNs) are not easy to develop due to two main factors: lack of efficient supervised learning algorithms, and high computational requirements that ultimately lead to higher power consumption and higher cost. In this article, we present an FPGA-based neuromorphic system capable of training SNNs efficiently. The Tempotron learning rule along with population coding is adopted for SNN learning to achieve a high level of classification accuracy. To blend cost efficiency with high throughput, integration of both integrate-and-fire (IF) and leaky integrate-and-fire (LIF) neurons is proposed. Moreover, the post-synaptic potential (PSP) kernel function for the LIF neuron is modeled using slopes. This novel solution obviates the need for multipliers and memory accesses for kernel computations. Experimental results show that a speedup of about 15 × can be obtained on a general-purpose Von-Neumann device if the proposed scheme is adopted. Moreover, the proposed neuromorphic design is fully parallelized and can achieve a maximum throughput of about 2460 × 10 6 4-input samples per second, while consuming only 13.6 slice registers per synapse and 89.5 look-up tables (LuTs) per synapse on Virtex 6 FPGA. The system can classify an input sample in about 4.88 ns. [ABSTRACT FROM AUTHOR]

The results of first-step research activity are presented for realizing an envisioned "event radio" capability that mimics neuromorphic event-based camera processing. The energy efficiency of neuromorphic processing is orders of magnitude higher than traditional von Neumann-based processing and is realized through synergistic design of brain-inspired software and hardware computing elements. Relative to event-based cameras, the development of event-based hardware devices supporting Radio Frequency (RF) applications is severely lagging and considerable interest remains in obtaining neuromorphic efficiency through event-based RF signal processing. In the Operational Technology (OT) protection arena, this includes efficient software computing capability to provide reliable device classification. A Random Forest (RndF) classifier is considered here as a reliable precursor to obtaining Spiking Neural Network (SNN) benefits. Both 1D and 2D eventized RF fingerprints are generated for bursts from NDev = 8 WirelessHART devices. Average correct classification (%C) results show that 2D fingerprinting is best overall using detected events in burst Gabor transform responses. This includes %C ≥ 90% under multiple access interference conditions using an average of NEPB ≥ 400 detected events per burst. This is sufficiently promising to motivate next-step activity aimed at (1) reducing fingerprint dimensionality and minimizing the required computational resources, and (2) transitioning to a neuromorphic-friendly SNN classifier—two significant steps toward developing the necessary computing elements to achieve the full benefits of neuromorphic processing in the envisioned RF event radio. [ABSTRACT FROM AUTHOR]

In this study, we explore spintronic synapses composed of several Magnetic Tunnel Junctions (MTJs), leveraging their attractive characteristics such as endurance, nonvolatility, stochasticity, and energy efficiency for hardware implementation of unsupervised neuromorphic systems. Spiking Neural Networks (SNNs) running on dedicated hardware are suitable for edge computing and IoT devices where continuous online learning and energy efficiency are important characteristics. We focus in this work on synaptic plasticity by conducting comprehensive electrical simulations to optimize the MTJ-based synapse design and find the accurate neuronal pulses that are responsible for the Spike Timing Dependent Plasticity (STDP) behavior. Most proposals in the literature are based on hardware-independent algorithms that require the network to store the spiking history to be able to update the weights accordingly. In this work, we developed a new learning rule, the Bi-Sigmoid STDP (B2STDP), which originates from the physical properties of MTJs. This rule enables immediate synaptic plasticity based on neuronal activity, leveraging in-memory computing. Finally, the integration of this learning approach within an SNN framework leads to a 91.71% accuracy in unsupervised image classification, demonstrating the potential of MTJ-based synapses for effective online learning in hardware-implemented SNNs. [ABSTRACT FROM AUTHOR]

Background. Brain–machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs. [ABSTRACT FROM AUTHOR]

In this work, a complementary metal‐oxide‐semiconductor (CMOS) based leaky‐integrate and fire neuron has been proposed and investigated for neuromorphic applications. The neuron has been designed in Cadence Virtuoso and validated experimentally. It has been observed that the neuron consumes a maximum energy of 68.87 fJ/spike. The response of the neuron to excitatory as well as inhibitory inputs has been studied. To verify the applicability, the proposed neuron has been explored for reconfigurable threshold logic to implement various linearly separable Boolean functions including OR, AND, NOT, NOR, and NAND. Moreover, the threshold tunability of the neuron has also been verified and this property has been exploited to design threshold‐controlled logic gates. Instead of adjusting the weights of the applied inputs, the functionality of such gates can be controlled by changing the threshold of the neuron, simplifying the synaptic architecture of a neural network. Finally, a multilayer network has been designed and the recognition ability of the proposed network for MNIST handwritten digits has been verified with an accuracy of 96.93%. [ABSTRACT FROM AUTHOR]

Organizations managing high-performance computing systems face a multitude of challenges, including overarching concerns such as overall energy consumption, microprocessor clock frequency limitations, and the escalating costs associated with chip production. Evidently, processor speeds have plateaued over the last decade, persisting within the range of 2 GHz to 5 GHz. Scholars assert that brain-inspired computing holds substantial promise for mitigating these challenges. The spiking neural network (SNN) particularly stands out for its commendable power efficiency when juxtaposed with conventional design paradigms. Nevertheless, our scrutiny has brought to light several pivotal challenges impeding the seamless implementation of large-scale neural networks (NNs) on silicon. These challenges encompass the absence of automated tools, the need for multifaceted domain expertise, and the inadequacy of existing algorithms to efficiently partition and place extensive SNN computations onto hardware infrastructure. In this paper, we posit the development of an automated tool flow capable of transmuting any NN into an SNN. This undertaking involves the creation of a novel graph-partitioning algorithm designed to strategically place SNNs on a network-on-chip (NoC), thereby paving the way for future energy-efficient and high-performance computing paradigms. The presented methodology showcases its effectiveness by successfully transforming ANN architectures into SNNs with a marginal average error penalty of merely 2.65%. The proposed graph-partitioning algorithm enables a 14.22% decrease in inter-synaptic communication and an 87.58% reduction in intra-synaptic communication, on average, underscoring the effectiveness of the proposed algorithm in optimizing NN communication pathways. Compared to a baseline graph-partitioning algorithm, the proposed approach exhibits an average decrease of 79.74% in latency and a 14.67% reduction in energy consumption. Using existing NoC tools, the energy-latency product of SNN architectures is, on average, 82.71% lower than that of the baseline architectures. [ABSTRACT FROM AUTHOR]

Amongst all types of cancer, breast cancer has become one of the most common cancers in the UK threatening millions of people's health. Early detection of breast cancer plays a key role in timely treatment for morbidity reduction. Compared to biopsy, which takes tissues from the lesion for further analysis, image-based methods are less time-consuming and pain-free though they are hampered by lower accuracy due to high false positivity rates. Nevertheless, mammography has become a standard screening method due to its high efficiency and low cost with promising performance. Breast mass, as the most palpable symptom of breast cancer, has received wide attention from the community. As a result, the past decades have witnessed the speeding development of computer-aided systems that are aimed at providing radiologists with useful tools for breast mass analysis based on mammograms. However, the main issues of these systems include low accuracy and require enough computational power on a large scale of datasets. To solve these issues, we developed a novel breast mass classification system called DF-dRVFL. On the public dataset DDSM with more than 3500 images, our best model based on deep random vector functional link network showed promising results through five-cross validation with an averaged AUC of 0.93 and an average accuracy of 81.71 % . Compared to sole deep learning based methods, average accuracy has increased by 0.38. Compared with the state-of-the-art methods, our method showed better performance considering the number of images for evaluation and the overall accuracy. [ABSTRACT FROM AUTHOR]

Memristive devices being applied in neuromorphic computing are envisioned to significantly improve the power consumption and speed of future computing platforms. The materials used to fabricate such devices will play a significant role in their viability. Graphene is a promising material, with superb electrical properties and the ability to be produced in large volumes. In this paper, we demonstrate that a graphene-based memristive device could potentially be used as synapses within spiking neural networks (SNNs) to realise spike timing-dependant plasticity for unsupervised learning in an efficient manner. Specifically, we verify the operation of two SNN architectures tasked for single-digit (0–9) classification: (i) a single layer network, where inputs are presented in 5 × 5 pixel resolution, and (ii) a larger network capable of classifying the dataset. Our work presents the first investigation and large-scale simulation of the use of graphene memristive devices to perform a complex pattern classification task. In favour of reproducible research, we will make our code and data publicly available. This can pave the way for future research in using graphene devices with memristive capabilities in neuromorphic computing architectures. [ABSTRACT FROM AUTHOR]

The primary approaches used to train spiking neural networks (SNNs) involve either training artificial neural networks (ANNs) first and then transforming them into SNNs, or directly training SNNs using surrogate gradient techniques. Nevertheless, both of these methods encounter a shared challenge: they rely on frame-based methodologies, where asynchronous events are gathered into synchronous frames for computation. This strays from the authentic asynchronous, event-driven nature of SNNs, resulting in notable performance degradation when deploying the trained models on SNN simulators or hardware chips for real-time asynchronous computation. To eliminate this performance degradation, we propose a hardware-based SNN proxy learning method that is called Chip-In-Loop SNN Proxy Learning (CIL-SPL). This approach eectively eliminates the performance degradation caused by the mismatch between synchronous and asynchronous computations. To demonstrate the eectiveness of our method, we trained models using public datasets such as N-MNIST and tested them on the SNN simulator or hardware chip, comparing our results to those classical training method [ABSTRACT FROM AUTHOR]

In view of the soaring demand of highly scalable and energy-efficient neuron devices for future neuromorphic computing, this work demonstrates a novel double-gate ferroelectric junctionless field effect transistor (DG-FE-JLFET) neuron in 20 nm technology node. The proposed device has a homogenously doped structure with GaAs as channel material and HfZrO2 as gate oxide. Using the calibrated simulations in Atlas TCAD, it is confirmed that the proposed neuron accurately mimics the spiking behavior of the biological neuron with an energy consumption of 24 aJ/spike, which is ~ 105 folds lesser than the previously proposed single transistor neurons. The proposed design does not need additional circuitry to operate. This greatly simplifies design complexity and can also achieve higher neuron density which is important for designing large scale integration neuromorphic chips. In contrast to the previously reported JLFET neurons that work on impact ionization phenomenon, DG-FE-JLFET works on tunnelling mechanism that eradicates the need to create virtual potential well to accommodate charge carriers in the body. Finally, to validate the practical applicability, the proposed neuron has been explored for image classification with an accuracy of 93.28%. [ABSTRACT FROM AUTHOR]

In recent years, implementing reinforcement learning in autonomous mobile robots (AMRs) has become challenging. Traditional methods face complex trials, long convergence times, and high computational requirements. This paper introduces an innovative strategy using a customized spiking neural network (SNN) for autonomous learning and control of mobile robots (AMR) in unknown environments. The model combines spike-timing-dependent plasticity (STDP) with dopamine modulation for learning. It utilizes the Izhikevich neuron model, leading to biologically inspired and computationally efficient control systems that adapt to changing environments. The performance of the model is evaluated in a simulated environment, replicating real-world scenarios with obstacles. In the initial training phase, the model faces significant challenges. Integrating brain-inspired learning, dopamine, and the Izhikevich neuron model adds complexity. The model achieves an accuracy rate of 33% in reaching its target during this phase. Collisions with obstacles occur 67% of the time, indicating the struggle of the model to adapt to complex obstacles. However, the model's performance improves as the study progresses to the testing phase after the robot has learned. Its accuracy surges to 94% when reaching the target, and collisions with obstacles reduce it to 6%. This shift demonstrates the adaptability and problem-solving capabilities of the model in the simulated environment, making it more competent for real-world applications. [ABSTRACT FROM AUTHOR]

Foundation models trained on vast quantities of data have demonstrated impressive performance in capturing complex nonlinear relationships and accurately predicting neuronal responses. Due to the fact that deep learning neural networks depend on massive amounts of data samples and high energy consumption, foundation models based on spiking neural networks (SNNs) have the potential to significantly reduce calculation costs by training on neuromorphic hardware. In this paper, a visually inspired computational model composed of an SNN and echo state network (ESN) is proposed for the recognition of optic flow. The visually inspired SNN model serves as a foundation model that is trained using spike-timing-dependent plasticity (STDP) for extracting core features. The ESN model makes readout decisions for recognition tasks using the linear regression method. The results show that STDP can perform similar functions as non-negative matrix decomposition (NMF), i.e., generating sparse and linear superimposed readouts based on basis flow fields. Once the foundation model is fully trained from enough input samples, it can considerably reduce the training samples required for ESN readout learning. Our proposed SNN-based foundation model facilitates efficient and cost-effective task learning and could also be adapted to new stimuli that are not included in the training of the foundation model. Moreover, compared with the NMF algorithm, the foundation model trained using STDP does not need to be retrained during the testing procedure, contributing to a more efficient computational performance. [ABSTRACT FROM AUTHOR]

Spiking neural networks (SNNs) can be used in low-power and embedded systems e.g. neuromorphic chips due to their event-based nature. They preserve conventional artificial neural networks (ANNs) properties with lower computation and memory costs. The temporal coding in layers of convolutional SNNs has not yet been studied. In this paper, we exploit the spatio-temporal feature extraction property of convolutional SNNs. Based on our analysis, we have shown that the shallow convolutional SNN outperforms spatio-temporal feature extractor methods such as C3D, ConvLstm, and cascaded Conv and LSTM. Furthermore, we present a new deep spiking architecture to tackle real-world classification and activity recognition tasks. This model is trained with our proposed hybrid training method. The proposed architecture achieved superior performance compared to other SNN methods on NMNIST (99.6%), DVS-CIFAR10 (69.2%), and DVS-Gesture (96.7%). Also, it achieves comparable results compared to ANN methods on UCF-101 (42.1%) and HMDB-51 (21.5%) datasets. [ABSTRACT FROM AUTHOR]

This work aims to present a novel energy-efficient single transistor leaky integrate-and-fire neuron for future neuromorphic computing. It comprises of a SiGe-based MOSFET, having channel length of 400 nm. Using 2D simulation, it has been verified that the proposed SiGe-based single transistor neuron accurately mimics the spiking behavior of the biological neuron, while eliminating the need of external circuitry and exorbitant energy consumption. The neuron consumes energy of 3.8 pJ/spike, which is 11.8 times and 2.1 times lesser than the previously proposed Si-based and Ge-based single transistor neurons, respectively. It also shows improvement in terms of controllability, simplicity, integration density, and fabrication process. By designing threshold logic gates, the proposed neuron has been employed to implement universal digital logic functions, such as NAND and NOR. Finally, the recognition ability for MNIST handwritten digits has been verified. It has been confirmed that besides imitating the neuronal behavior accurately, the proposed neuron can also be used in practical spiking neural networks for image classification with an accuracy of 93.79%. [ABSTRACT FROM AUTHOR]

In this study, we explore spintronic synapses composed of several Magnetic Tunnel Junctions (MTJs), leveraging their attractive characteristics such as endurance, nonvolatility, stochasticity, and energy efficiency for hardware implementation of unsupervised neuromorphic systems. Spiking Neural Networks (SNNs) running on dedicated hardware are suitable for edge computing and IoT devices where continuous online learning and energy efficiency are important characteristics. We focus in this work on synaptic plasticity by conducting comprehensive electrical simulations to optimize the MTJ-based synapse design and find the accurate neuronal pulses that are responsible for the Spike Timing Dependent Plasticity (STDP) behavior. Most proposals in the literature are based on hardware-independent algorithms that require the network to store the spiking history to be able to update the weights accordingly. In this work, we developed a new learning rule, the Bi-Sigmoid STDP (B2STDP), which originates from the physical properties of MTJs. This rule enables immediate synaptic plasticity based on neuronal activity, leveraging in-memory computing. Finally, the integration of this learning approach within an SNN framework leads to a 91.71% accuracy in unsupervised image classification, demonstrating the potential of MTJ-based synapses for effective online learning in hardware-implemented SNNs.

Analog neuromorphic prototyping is essential for designing and testing spiking neuron models that use memristive devices as synapses. These prototypes can have various circuit configurations, implying different response behaviors that custom silicon designs lack. The prototype’s behavior results can be optimized for a specific foundry node, which can be used to produce a customized on-chip parallel deep neural network. Spiking neurons mimic how the biological neurons in the brain communicate through electrical potentials. Doing so enables more powerful and efficient functionality than traditional artificial neural networks that run on von Neumann computers or graphic processing unit-based platforms. Therefore, on-chip parallel deep neural network technology can accelerate deep learning processing, aiming to exploit the brain’s unique features of asynchronous and event-driven processing by leveraging the neuromorphic hardware’s inherent parallelism and analog computation capabilities. This paper presents the design and implementation of a leaky integrate-and-fire (LIF) neuron prototype implemented with commercially available components on a PCB board. The simulations conducted in LTSpice agree well with the electrical test measurements. The results demonstrate that this design can be used to interconnect many boards to build layers of physical spiking neurons, with spike-timing-dependent plasticity as the primary learning algorithm, contributing to the realization of experiments in the early stage of adopting analog neuromorphic computing.

SNNTool is an efficient utility designed for researchers and developers, providing methods for building, training, and applying various Sampling Neural Networks (SNNs). SNN is a novel neural network with high accuracy, fast convergence, low computational burden, and reliability. SNN extends the diversification of neural networks and their methods, opens up new ideas in neural network bionic research, and provides new application directions. SNNTool provides a simple and user-friendly programming interface and flexible control ability for the structure and parameters of SNNs models. SNNTool brings a positive impetus to SNN-related research work and provides assistance in simplifying and improving SNNs models. The experimental results demonstrated the effectiveness of the models and tools.

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

The application of the structure and principles of the human brain opens up great opportunities for creating artificial systems based on silicon technology. The energy efficiency and performance of a biosimilar architecture can be significantly higher compared to the traditional von Neumann architecture. This paper presents an overview of the most promising artificial neural network (ANN) and spiking neural network (SNN) architectures for biosimilar systems, called neuromorphic systems. Devices for biosimilar systems, such as memristors and ferroelectric transistors, are considered for use as artificial synapses that determine the possibility of creating various architectures of neuromorphic systems; methods and rules for training structures to work correctly when mimicking biological learning rules, such as long-term synaptic plasticity. Problems hindering the implementation of biosimilar systems and examples of architectures that have been practically implemented are discussed. [ABSTRACT FROM AUTHOR]

The face is the most popular biometric trait for human recognition. The goal of a face identification system is to mimic the human recognition process and automate applications such as border control, passport control, criminal investigation, and terrorist identification. In this study, we examine multi-view face identification systems, particularly when there are limited samples of images per angle of view per identity. We propose a multi-view face identification system based on the Siamese Neural Network (SNN), and we evaluate its performance under two training scenarios: using only same-angle images and using both same-angle and different-angle images. Our system is also trained with only one image per angle for the training set. The results of our experiments on Umist and Schneiderman databases demonstrate that the proposed SNN model is the optimal solution for few-shot multi-view face identification, with an accuracy of 74.4% compared to 37% for the VGGFace model and 77% compared to 76% for a CNN model trained from scratch, when using one image per angle for the training set on the Schneiderman database with an angle of view + 10. The accuracy was 59% for the VGGFace model. The proposed model can be downloaded from this link: https://github.com/Majdouline-Meddad/SNN-for-Multi-view-face-identification. [ABSTRACT FROM AUTHOR]

Background. Brain–machine interfaces (BMIs) offer users the ability to directly communicate with digital devices through neural signals decoded with machine learning (ML)-based algorithms. Spiking Neural Networks (SNNs) are a type of Artificial Neural Network (ANN) that operate on neural spikes instead of continuous scalar outputs. Compared to traditional ANNs, SNNs perform fewer computations, use less memory, and mimic biological neurons better. However, SNNs only retain information for short durations, limiting their ability to capture long-term dependencies in time-variant data. Here, we propose a novel spike-weighted SNN with spiking long short-term memory (swSNN-SLSTM) for a regression problem. Spike-weighting captures neuronal firing rate instead of membrane potential, and the SLSTM layer captures long-term dependencies. Methods. We compared the performance of various ML algorithms during decoding directional movements, using a dataset of microelectrode recordings from a macaque during a directional joystick task, and also an open-source dataset. We thus quantified how swSNN-SLSTM performed compared to existing ML models: an unscented Kalman filter, LSTM-based ANN, and membrane-based SNN techniques. Result. The proposed swSNN-SLSTM outperforms both the unscented Kalman filter, the LSTM-based ANN, and the membrane based SNN technique. This shows that incorporating SLSTM can better capture long-term dependencies within neural data. Also, our proposed swSNN-SLSTM algorithm shows promise in reducing power consumption and lowering heat dissipation in implanted BMIs.

The potential low-energy feature of the spiking neural network (SNN) engages the attention of the AI community. Only CPU-involved SNN processing inevitably results in an inherently long temporal span in the cases of large models and massive datasets. This study introduces the MAC array, a parallel architecture on each processing element (PE) of SpiNNaker 2, into the computational process of SNN inference. Based on the work of single-core optimization algorithms, we investigate the parallel acceleration algorithms for collaborating with multi-core MAC arrays. The proposed Echelon Reorder model information densification algorithm, along with the adapted multi-core two-stage splitting and authorization deployment strategies, achieves efficient spatio-temporal load balancing and optimization performance. We evaluate the performance by benchmarking a wide range of constructed SNN models to research on the influence degree of different factors. We also benchmark with two actual SNN models (the gesture recognition model of the real-world application and balanced random cortex-like network from neuroscience) on the neuromorphic multi-core hardware SpiNNaker 2. The echelon optimization algorithm with mixed processors realizes 74.28% and 85.78% memory footprint of the original MAC calculation on these two models, respectively. The execution time of echelon algorithms using only MAC or mixed processors accounts for ≤24.56% of the serial ARM baseline. Accelerating SNN inference with algorithms in this study is essentially the general sparse matrix-matrix multiplication (SpGEMM) problem. This article explicitly expands the application field of the SpGEMM issue to SNN, developing novel SpGEMM optimization algorithms fitting the SNN feature and MAC array. [ABSTRACT FROM AUTHOR]

In this paper, the object of the research is the implementation of artificial neural networks (ANN) on FPGA. The problem to be solved is the construction of a mathematical model used to determine the compliance of FPGA computing resources with the requirements of neural networks, depending on their type, structure, and size. The number of its LUT (Look-up table - the basic FPGA structure that performs logical operations) is considered as a computing resource of the FPGA. The search for the required mathematical model was carried out using experimental measurements of the required number of LUTs for the implementation on the FPGA of the following types of ANNs: - MLP (Multilayer Perceptron); - LSTM (Long Short-Term Memory); - CNN (Convolutional Neural Network); - SNN (Spiking Neural Network); - GAN (Generative Adversarial Network). Experimental studies were carried out on the FPGA model HAPS-80 S52, during which the required number of LUTs was measured depending on the number of layers and the number of neurons on each layer for the above types of ANNs. As a result of the research, specific types of functions depending on the required number of LUTs on the type, number of layers, and neurons for the most commonly used types of ANNs in practice were determined. A feature of the results obtained is the fact that with a sufficiently high accuracy, it was possible to determine the analytical form of the functions that describe the dependence of the required number of LUT FPGA for the implementation of various ANNs on it. According to calculations, GAN uses 17 times less LUT compared to CNN. And SNN and MLP use 80 and 14 times less LUT compared to LSTM. The results obtained can be used for practical purposes when it is necessary to make a choice of any FPGA for the implementation of an ANN of a certain type and structure on it. [ABSTRACT FROM AUTHOR]

In recent years, the effectiveness of a spiking neural network (SNN) for Electromyography (EMG) pattern recognition has been validated, but there is a lack of comprehensive consideration of the problems of heavy training burden, poor robustness, and high energy consumption in the application of actual myoelectric control systems. In order to explore the feasibility of the application of SNN in actual myoelectric control systems, this paper investigated an EMG pattern recognition scheme based on SNN. To alleviate the differences in EMG distribution caused by electrode shifts and individual differences, the adaptive threshold encoding was applied to gesture sample encoding. To improve the feature extraction ability of SNN, the leaky-integrate-and-fire (LIF) neuron that combines voltage-current effect was adopted as a spike neuron model. To balance recognition accuracy and power consumption, experiments were designed to determine encoding parameter and LIF neuron release threshold. By conducting the gesture recognition experiments considering different training test ratios, electrode shifts, and user independences on the nine-gesture highdensity and low-density EMG datasets respectively, the advantages of the proposed SNN-based scheme have been verified. Compared with a Convolutional Neural Network (CNN), Long Short-Term Memory Network (LSTM) and Linear Discriminant Analysis (LDA), SNN can effectively reduce the number of repetitions in the training set, and its power consumption was reduced by 1-2 orders of magnitude. For the high-density and low-density EMG datasets, SNN improved the overall average accuracies by about (0.99 ~ 14.91%) under different training test ratios. For the high-density EMG dataset, the accuracy of SNN was improved by (0.94 ~ 13.76%) under electrode-shift condition and (3.81 ~ 18.95%) in userindependent case. The advantages of SNN in alleviating the user training burden, reducing power consumption, and improving robustness are of great significance for the implementation of user-friendly low-power myoelectric control systems. [ABSTRACT FROM AUTHOR]

For the next coming years, metaverse, digital twin and autonomous vehicle applications are the leading technologies for many complex applications hitherto inaccessible such as health and life sciences, smart home, smart agriculture, smart city, smart car and logistics, Industry 4.0, entertainment (video game) and social media applications, due to recent tremendous developments in process modeling, supercomputing, cloud data analytics (deep learning, etc.), communication network and AIoT/IIoT/IoT technologies. AIoT/IIoT/IoT is a crucial research field because it provides the essential data to fuel metaverse, digital twin, real-time Industry 4.0 and autonomous vehicle applications. However, the science of AIoT is inherently multidisciplinary, and therefore, it is difficult for readers to understand its evolution and impacts. Our main contribution in this article is to analyze and highlight the trends and challenges of the AIoT technology ecosystem including core hardware (MCU, MEMS/NEMS sensors and wireless access medium), core software (operating system and protocol communication stack) and middleware (deep learning on a microcontroller: TinyML). Two low-powered AI technologies emerge: TinyML and neuromorphic computing, but only one AIoT/IIoT/IoT device implementation using TinyML dedicated to strawberry disease detection as a case study. So far, despite the very rapid progress of AIoT/IIoT/IoT technologies, several challenges remain to be overcome such as safety, security, latency, interoperability and reliability of sensor data, which are essential characteristics to meet the requirements of metaverse, digital twin, autonomous vehicle and Industry 4.0. applications. [ABSTRACT FROM AUTHOR]

Due to the continuous growth of hardware neuromorphic systems, the need for high-speed, low-power, and energy-efficient computer architectures is increasing. Memristors-based neural networks are a promising solution for low-power neuromorphic systems. Spiking neural networks (SNNs) have been considered the optimal hardware implementation of these systems. Previous studies of SNNs rely on complex circuit to implement in situ bio-plausible STDP learning using memristors, which is computationally challenging. In this paper, we propose an SNN that performs both in situ learning and inference using a new efficient programming technique. Our interest lies in applying the winner-takes-all (WTA) mechanism in the SNN architecture used with recurrently connected neurons, allowing real-time processing of patterns. We provide a programming circuit that enables better weight modulation with less power consumption and less space occupation, using a generalized enhanced memristor model (EGM). The proposed programming circuit is connected to leaky integrate-and-fire (LIF) neurons included in a crossbar architecture to perform recognition task. The simulation results not only prove the correctness of the design, but also offer an efficient implementation in terms of area, energy, accuracy, as well as the ability to classify 40,000 images per second. [ABSTRACT FROM AUTHOR]

Computer recognition of human activity is an important area of research in computer vision. Human activity recognition (HAR) involves identifying human activities in real-life contexts and plays an important role in interpersonal interaction. Artificial intelligence usually identifies activities by analyzing data collected using different sources. These can be wearable sensors, MEMS devices embedded in smartphones, cameras, or CCTV systems. As part of HAR, computer vision technology can be applied to the recognition of the emotional state through facial expressions using facial positions such as the nose, eyes, and lips. Human facial expressions change with different health states. Our application is oriented toward the detection of the emotional health of subjects using a self-normalizing neural network (SNN) in cascade with an ensemble layer. We identify the subjects' emotional states through which the medical staff can derive useful indications of the patient's state of health. [ABSTRACT FROM AUTHOR]

Abstract This paper aims to improve the quality of reconstructed visual stimuli and reduce the computational complexity of the visual stimuli reconstruction processes in the form of functional Magnetic Resonance Imaging (fMRI) profiles. The preceding work envisions the non-cognitive contents of brain activity vain to integrate visual data of diverse hierarchical levels. Existing approaches such as Deep Canonically Correlated Auto Encoder detect the significant challenges of reconstructing visual stimuli from brain activity: fMRI noise, large dimensionality of a limited number of data instances, and complex structure of visual stimuli. In this activity, we will also analyze the scope for utilizing the spatiotemporal data to resolve the neural correlates of visual stimulus representations and reconstruct the resembling visual stimuli. The purpose of this work is to manipulate those suffering from developmental disabilities. A novel Siamese conditional Generative Adversarial Network (ScGAN) approach is proposed to resolve these significant issues. The key features of ScGAN are as follows: 1. Siamese Neural Network (SNN) is a dimensionality reduction approach that takes as visual stimulus information alloy component and its goals to discover each of them effectively. It shows the critical component of visual stimuli. 2. In a conditional Generative Adversarial Network, the labels portrayan expansion to a latent variable to better generate and discriminate visual stimuli. Experiments on four fMRI datasets prove that our technique can reconstruct visual stimuli precisely. The performance metrics are evaluated by Mean Squared Error (MSE), Accuracy, Pearson Correlation Coefficient (PCC), Losses, Structural Similarity Index (SSIM), Computational Time, etc. It proves that the proposed method yields better outcomes in terms of accuracy.

Organizations managing high-performance computing systems face a multitude of challenges, including overarching concerns such as overall energy consumption, microprocessor clock frequency limitations, and the escalating costs associated with chip production. Evidently, processor speeds have plateaued over the last decade, persisting within the range of 2 GHz to 5 GHz. Scholars assert that brain-inspired computing holds substantial promise for mitigating these challenges. The spiking neural network (SNN) particularly stands out for its commendable power efficiency when juxtaposed with conventional design paradigms. Nevertheless, our scrutiny has brought to light several pivotal challenges impeding the seamless implementation of large-scale neural networks (NNs) on silicon. These challenges encompass the absence of automated tools, the need for multifaceted domain expertise, and the inadequacy of existing algorithms to efficiently partition and place extensive SNN computations onto hardware infrastructure. In this paper, we posit the development of an automated tool flow capable of transmuting any NN into an SNN. This undertaking involves the creation of a novel graph-partitioning algorithm designed to strategically place SNNs on a network-on-chip (NoC), thereby paving the way for future energy-efficient and high-performance computing paradigms. The presented methodology showcases its effectiveness by successfully transforming ANN architectures into SNNs with a marginal average error penalty of merely 2.65%. The proposed graph-partitioning algorithm enables a 14.22% decrease in inter-synaptic communication and an 87.58% reduction in intra-synaptic communication, on average, underscoring the effectiveness of the proposed algorithm in optimizing NN communication pathways. Compared to a baseline graph-partitioning algorithm, the proposed approach exhibits an average decrease of 79.74% in latency and a 14.67% reduction in energy consumption. Using existing NoC tools, the energy-latency product of SNN architectures is, on average, 82.71% lower than that of the baseline architectures.

Time–frequency analysis plays a crucial role in various fields, including signal processing and feature extraction. In this article, we propose an alternative and innovative method for time–frequency analysis using a biologically inspired spiking neural network (SNN), encompassing both a specific spike-continuous-time-neuron-based neural architecture and an adaptive learning rule. We aim to efficiently detect frequencies embedded in a given signal for the purpose of feature extraction. To achieve this, we suggest using an SN-based network functioning as a resonator for the detection of specific frequencies. We developed a modified supervised spike timing-dependent plasticity learning rule to effectively adjust the network parameters. Unlike traditional methods for time–frequency analysis, our approach obviates the need to segment the signal into several frames, resulting in a streamlined and more effective frequency analysis process. Simulation results demonstrate the efficiency of the proposed method, showcasing its ability to detect frequencies and generate a Spikegram akin to the fast Fourier transform (FFT) based spectrogram. The proposed approach is applied to analyzing EEG signals, demonstrating an accurate correlation to the equivalent FFT transform. Results show a success rate of 94.3% in classifying EEG signals.

In recent years, implementing reinforcement learning in autonomous mobile robots (AMRs) has become challenging. Traditional methods face complex trials, long convergence times, and high computational requirements. This paper introduces an innovative strategy using a customized spiking neural network (SNN) for autonomous learning and control of mobile robots (AMR) in unknown environments. The model combines spike-timing-dependent plasticity (STDP) with dopamine modulation for learning. It utilizes the Izhikevich neuron model, leading to biologically inspired and computationally efficient control systems that adapt to changing environments. The performance of the model is evaluated in a simulated environment, replicating real-world scenarios with obstacles. In the initial training phase, the model faces significant challenges. Integrating brain-inspired learning, dopamine, and the Izhikevich neuron model adds complexity. The model achieves an accuracy rate of 33% in reaching its target during this phase. Collisions with obstacles occur 67% of the time, indicating the struggle of the model to adapt to complex obstacles. However, the model’s performance improves as the study progresses to the testing phase after the robot has learned. Its accuracy surges to 94% when reaching the target, and collisions with obstacles reduce it to 6%. This shift demonstrates the adaptability and problem-solving capabilities of the model in the simulated environment, making it more competent for real-world applications.