Hyperdimensional decoding of spiking neural networks

Due to energy efficiency, spiking neural networks (SNNs) have gradually been considered as an alternative to convolutional neural networks (CNNs) in various machine learning tasks. In image recognition tasks, leveraging the superior capability of CNNs, the CNN–SNN conversion is considered one of the most successful approaches to training SNNs. However, previous works assume a rather long inference time period called inference latency to be allowed, while having a trade-off between inference latency and accuracy. One of the main reasons for this phenomenon stems from the difficulty in determining proper a firing threshold for spiking neurons. The threshold determination procedure is called a threshold balancing technique in the CNN–SNN conversion approach. This paper proposes a CNN–SNN conversion method with a new threshold balancing technique that obtains converted SNN models with good accuracy even with low latency. The proposed method organizes the SNN models with soft-reset IF spiking neurons. The threshold balancing technique estimates the thresholds for spiking neurons based on the maximum input current in a layerwise and channelwise manner. The experiment results have shown that our converted SNN models attain even higher accuracy than the corresponding trained CNN model for the MNIST dataset with low latency. In addition, for the Fashion-MNIST and CIFAR-10 datasets, our converted SNNs have shown less conversion loss than other methods in low latencies. The proposed method can be beneficial in deploying efficient SNN models for recognition tasks on resource-limited systems because the inference latency is strongly associated with energy consumption.

Recently, brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. However, these SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. Given that each neural coding scheme possesses its own merits and drawbacks, these SNNs encounter challenges in achieving optimal performance such as accuracy, response time, efficiency, and robustness, all of which are crucial for practical applications. In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes. As an initial exploration in this direction, we propose a hybrid neural coding and learning framework, which encompasses a neural coding zoo with diverse neural coding schemes discovered in neuroscience. Additionally, it incorporates a flexible neural coding assignment strategy to accommodate task-specific requirements, along with novel layer-wise learning methods to effectively implement hybrid coding SNNs. We demonstrate the superiority of the proposed framework on image classification and sound localization tasks. Specifically, the proposed hybrid coding SNNs achieve comparable accuracy to state-of-the-art SNNs, while exhibiting significantly reduced inference latency and energy consumption, as well as high noise robustness. This study yields valuable insights into hybrid neural coding designs, paving the way for developing high-performance neuromorphic systems.

Spiking Neural Networks (SNNs) are a promising research paradigm for low power edge-based computing. Recent works in SNN backpropagation has enabled training of SNNs for practical tasks. However, since spikes are binary events in time, standard loss formulations are not directly compatible with spike output. As a result, current works are limited to using mean-squared loss of spike count. In this paper, we formulate the output probability interpretation from the spike count measure and introduce spike-based negative log-likelihood measure which are more suited for classification tasks especially in terms of the energy efficiency and inference latency. We compare our loss measures with other existing alternatives and evaluate using classification performances on three neuromorphic benchmark datasets: NMNIST, DVS Gesture and N-TIDIGITS18. In addition, we demonstrate state of the art performances on these datasets, achieving faster inference speed and less energy consumption.

Heart failure (HF) continues to be one of the world’s most prevalent causes of hospitalization and premature death, highlighting the urgent need for diagnostic approaches that are accurate, non-invasive, and cost-efficient. Recent advances suggest that speech carries physiological signatures of cardiopulmonary function, enabling voice-based biomarkers to act as indicators of disease progression. This study presents a comparative framework that evaluates Convolutional Neural Networks (CNNs) and Spiking Neural Networks (SNNs) for detecting HF from vocal acoustics. A curated dataset of patient speech samples was pre-processed to extract Mel-Frequency Cepstral Coefficients (MFCCs), log-Mel spectrograms, and prosodic features capturing rhythm and intensity variations. Both CNN and SNN models were trained under identical conditions with ten-fold cross-validation to ensure fairness and reproducibility. While CNN achieved 91.2 % accuracy, 89.5 % sensitivity, and ROC-AUC = 0.93, the SNN consistently surpassed it with 94.6 % accuracy, 93.8 % sensitivity, and ROC-AUC = 0.96, alongside a 43 % reduction in inference latency and nearly 40 % lower energy consumption. SHAP-based explainability revealed that spectral and prosodic cues jointly influenced model predictions, and ablation experiments confirmed the advantage of multimodal feature fusion. These findings demonstrate that SNNs combine clinical interpretability with energy-aware computation, making them ideal for edge-AI deployment in low-resource healthcare environments. The work establishes SNNs as a biologically inspired and computationally efficient paradigm for real-time voice-based cardiovascular screening.

Spiking Neural Networks (SNNs) are a pathway that could potentially empower low-power event-driven neuromorphic hardware due to their spatio-temporal information processing capability and high biological plausibility. Although SNNs are currently more efficient than artificial neural networks (ANNs), they are not as accurate as ANNs. Error backpropagation is the most common method for directly training neural networks, promoting the prosperity of ANNs in various deep learning fields. However, since the signals transmitted in the SNN are non-differentiable discrete binary spike events, the activation function in the form of spikes presents difficulties for the gradient-based optimization algorithms to be directly applied in SNNs, leading to a performance gap (i.e., accuracy and latency) between SNNs and ANNs. This paper introduces a new learning algorithm, called SSTDP, which bridges the gap between backpropagation (BP)-based learning and spike-time-dependent plasticity (STDP)-based learning to train SNNs efficiently. The scheme incorporates the global optimization process from BP and the efficient weight update derived from STDP. It not only avoids the non-differentiable derivation in the BP process but also utilizes the local feature extraction property of STDP. Consequently, our method can lower the possibility of vanishing spikes in BP training and reduce the number of time steps to reduce network latency. In SSTDP, we employ temporal-based coding and use Integrate-and-Fire (IF) neuron as the neuron model to provide considerable computational benefits. Our experiments show the effectiveness of the proposed SSTDP learning algorithm on the SNN by achieving the best classification accuracy 99.3% on the Caltech 101 dataset, 98.1% on the MNIST dataset, and 91.3% on the CIFAR-10 dataset compared to other SNNs trained with other learning methods. It also surpasses the best inference accuracy of the directly trained SNN with 25~32× less inference latency. Moreover, we analyze event-based computations to demonstrate the efficacy of the SNN for inference operation in the spiking domain, and SSTDP methods can achieve 1.3~37.7× fewer addition operations per inference. The code is available at: https://github.com/MXHX7199/SNN-SSTDP.

Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical.

Due to the advantages of low energy consumption, high robustness and fast inference speed, Spiking Neural Networks (SNNs), with good biological interpretability and the potential to be applied on neuromorphic hardware, are regarded as the third generation of Artificial Neural Networks (ANNs). Despite having so many advantages, the biggest challenge encountered by spiking neural networks is training difficulty caused by the non-differentiability of spike signals. ANN-SNN conversion is an effective method that solves the training difficulty by converting parameters in ANNs to those in SNNs through a specific algorithm. However, the ANN-SNN conversion method also suffers from accuracy degradation and long inference time. In this paper, we reanalyzed the relationship between Integrate-and-Fire (IF) neuron model and ReLU activation function, proposed a StepReLU activation function more suitable for SNNs under membrane potential encoding, and used it to train ANNs. Then we converted the ANNs to SNNs with extremely small conversion error and introduced leakage mechanism to the SNNs and get the final models, which have high accuracy, low latency and good robustness, and have achieved the state-of-the-art performance on various datasets such as CIFAR and ImageNet.

Recently, brain-inspired computing models have shown great potential to outperform today’s deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust cognitive learning. Despite the success, these two brain-inspired models have different strengths. While SNN mimics the physical properties of the human brain, HDC models the brain on a more abstract and functional level. Their design philosophies demonstrate complementary patterns that motivate their combination. With the help of the classical psychological model on memory, we propose SpikeHD, the first framework that fundamentally combines Spiking neural network and hyperdimensional computing. SpikeHD generates a scalable and strong cognitive learning system that better mimics brain functionality. SpikeHD exploits spiking neural networks to extract low-level features by preserving the spatial and temporal correlation of raw event-based spike data. Then, it utilizes HDC to operate over SNN output by mapping the signal into high-dimensional space, learning the abstract information, and classifying the data. Our extensive evaluation on a set of benchmark classification problems shows that SpikeHD provides the following benefit compared to SNN architecture: (1) significantly enhance learning capability by exploiting two-stage information processing, (2) enables substantial robustness to noise and failure, and (3) reduces the network size and required parameters to learn complex information.

The aim of this paper is design and develop energy efficient MANET network in wireless networks. One of the most significant and effective protocol based on low energy consumption and number of Ad-hoc is MANET as remote directing convention source nodes forward in network simulator. Less number of nodes in the network would give low energy usage or consumption as the nodes in the network exceeds or increases that will also increase the energy consumption in the network. The designed MANET system is tried with 9, 12, 15 and 18 number of nodes in a system using network simulation-2 (NS-2). Henceforth source node needs to restart over and over which brings about low energy consumption use and use, ectiveness is less and packet space is additionally less and throughput is likewise less and more start to finish delay. Arrangement of this issue in MANET convention which is advanced as the node doesn't advance when demand arrived at their first it checked there is low energy consumption (battery lifetime) and until the node energy consumption is more noteworthy than the limit. Designed MANET examinations of the energy consumption and node energy consumption by maintaining a strategic distance from the low number of nodes in a network. By contrasting energy consumption and node it demonstrates that MANET is far superior to existing framework 802.11 protocol convention based on battery lifetime, energy consumption, throughput, and power transmission. We have performed a comparison between EEM and AODV routing protocol considering different measuring parameters.

The aim of this paper is design and develop energy efficient MANET network in wireless networks. One of the most significant and effective protocol based on low energy consumption and number of Ad-hoc is MANET as remote directing convention source nodes forward in network simulator. Less number of nodes in the network would give low energy usage or consumption as the nodes in the network exceeds or increases that will also increase the energy consumption in the network. The designed MANET system is tried with 9, 12, 15 and 18 number of nodes in a system using network simulation-2 (NS-2). Henceforth source node needs to restart over and over which brings about low energy consumption use and use, ectiveness is less and packet space is additionally less and throughput is likewise less and more start to finish delay. Arrangement of this issue in MANET convention which is advanced as the node doesn't advance when demand arrived at their first it checked there is low energy consumption (battery lifetime) and until the node energy consumption is more noteworthy than the limit. Designed MANET examinations of the energy consumption and node energy consumption by maintaining a strategic distance from the low number of nodes in a network. By contrasting energy consumption and node it demonstrates that MANET is far superior to existing framework 802.11 protocol convention based on battery lifetime, energy consumption, throughput, and power transmission. We have performed a comparison between EEM and AODV routing protocol considering different measuring parameters.

Today's Machine Learning(ML) systems, especially those running in server farms running workloads such as Deep Neural Networks, which require billions of parameters and many hours to train a model, consume a significant amount of energy. To combat this, researchers have been focusing on new emerging neuromorphic computing models. Two of those models are Hyperdimensional Computing (HDC) and Spiking Neural Networks (SNNs), both with their own benefits. HDC has various desirable properties that other Machine Learning (ML) algorithms lack such as: robustness to noise in the system, simple operations, and high parallelism. SNNs are able to process event based signal data in an efficient manner. In this paper, we create HyperSpike, which utilizes a single, randomly initialized and untrained SNN layer as feature extractor connected to a trained HDC classifier. HDC is used to enable more efficient classification as well as provide robustness to errors. We experimentally show that HyperSpike is on average 31.5× more robust to errors than traditional SNNs. We also implement HyperSpike in hardware, and show that it is 10x faster and 2.6× more energy efficient over traditional SNN networks run on Intel's Loihi [1].

Spiking neural networks (SNNs) can utilize spatio-temporal information and have the characteristic of energy efficiency, being a good alternative to deep neural networks (DNNs). The event-driven information processing means that SNNs can reduce the expensive computation of DNNs and save a great deal of energy consumption. However, high training and inference latency is a limitation of the development of deeper SNNs. SNNs usually need tens or even hundreds of time steps during the training and inference process, which causes not only an increase in latency but also excessive energy consumption. To overcome this problem, we propose a novel training method based on backpropagation (BP) for ultra-low-latency (1–2 time steps) SNNs with multi-threshold. In order to increase the information capacity of each spike, we introduce the multi-threshold Leaky Integrate and Fired (LIF) model. The experimental results show that our proposed method achieves average accuracy of 99.56%, 93.08%, and 87.90% on MNIST, FashionMNIST, and CIFAR10, respectively, with only two time steps. For the CIFAR10 dataset, our proposed method achieves 1.12% accuracy improvement over the previously reported directly trained SNNs with fewer time steps.

Spiking Neural Networks (SNNs), widely known as the third generation of neural networks, encode input information temporally using sparse spiking events, which can be harnessed to achieve higher computational efficiency for cognitive tasks. However, considering the rapid strides in accuracy enabled by state-of-the-art Analog Neural Networks (ANNs), SNN training algorithms are much less mature, leading to accuracy gap between SNNs and ANNs. In this paper, we propose different SNN training methodologies, varying in degrees of biofidelity, and evaluate their efficacy on complex image recognition datasets. First, we present biologically plausible Spike Timing Dependent Plasticity (STDP) based deterministic and stochastic algorithms for unsupervised representation learning in SNNs. Our analysis on the CIFAR-10 dataset indicates that STDP-based learning rules enable the convolutional layers to self-learn low-level input features using fewer training examples. However, STDP-based learning is limited in applicability to shallow SNNs (≤4 layers) while yielding considerably lower than state-of-the-art accuracy. In order to scale the SNNs deeper and improve the accuracy further, we propose conversion methodology to map off-the-shelf trained ANN to SNN for energy-efficient inference. We demonstrate 69.96% accuracy for VGG16-SNN on ImageNet. However, ANN-to-SNN conversion leads to high inference latency for achieving the best accuracy. In order to minimize the inference latency, we propose spike-based error backpropagation algorithm using differentiable approximation for the spiking neuron. Our preliminary experiments on CIFAR-10 show that spike-based error backpropagation effectively captures temporal statistics to reduce the inference latency by up to 8× compared to converted SNNs while yielding comparable accuracy

Event cameras detect per-pixel brightness changes and output asynchronous event streams with high temporal resolution, high dynamic range, and low latency. However, the unstructured nature of event streams means that humans cannot analyze and interpret them in the same way as natural images. Event-based video reconstruction is a widely used method aimed at reconstructing intuitive videos from event streams. Most reconstruction methods based on traditional artificial neural networks (ANNs) have high energy consumption, which counteracts the low-power advantage of event cameras. Spiking neural networks (SNNs) are a new generation of event-driven neural networks that encode information via discrete spikes, which leads to greater computational efficiency. Previous methods based on SNNs overlooked the asynchronous nature of event streams, leading to reconstructions that suffer from artifacts, flickering, low contrast, etc. In this work, we analyze event streams and spiking neurons and explain poor reconstruction quality. We specifically propose a novel spatial-temporal heterogeneous (STH) spiking neuron suitable for reconstructing asynchronous event streams. The STH neuron adjusts the membrane decay coefficient adaptively and has better spatiotemporal perception. In addition, we propose a temporal-frequency calibration module (TFCM) based on the Fourier transform to improve the contrast of the reconstructions. On the basis of the above proposed neuron and module, we construct two SNN-based models, referred to as the STHSNN and TFCSNN. The goal of the former is to reduce the artifacts and flickering in reconstructions, whereas the latter focuses on enhancing the contrast. The experimental results demonstrate that our models can yield reconstructions in various scenarios, achieving better quality and lower energy consumption than previous SNNs. Specifically, the TFCSNN and STHSNN achieve top-2 performance among the SNN-based models, with energy consumption reductions of 3.48 times and 12.40 times, respectively.

Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures. However, due to the nondifferentiable nature of spiking neuronal functions, the standard error backpropagation algorithm is not directly applicable to SNNs. In this work, we propose a tandem learning framework that consists of an SNN and an artificial neural network (ANN) coupled through weight sharing. The ANN is an auxiliary structure that facilitates the error backpropagation for the training of the SNN at the spike-train level. To this end, we consider the spike count as the discrete neural representation in the SNN and design an ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN. The proposed tandem learning rule demonstrates competitive pattern recognition and regression capabilities on both the conventional frame- and event-based vision datasets, with at least an order of magnitude reduced inference time and total synaptic operations over other state-of-the-art SNN implementations. Therefore, the proposed tandem learning rule offers a novel solution to training efficient, low latency, and high-accuracy deep SNNs with low computing resources.