LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing

Sg-snn: a self-organizing spiking neural network based on temporal information

Neurodynamic observations indicate that the cerebral cortex evolved by self-organizing into functional networks, These networks, or distributed clusters of regions, display various degrees of attention maps based on input. Traditionally, the study of network self-organization relies predominantly on static data, overlooking temporal information in dynamic neuromorphic data. This paper proposes Temporal Self-Organizing (TSO) method for neuromorphic data processing using a spiking neural network. The TSO method incorporates information from multiple time steps into the selection strategy of the Best Matching Unit (BMU) neurons. It enables the coupled BMUs to radiate the weight across the same layer of neurons, ultimately forming a hierarchical self-organizing topographic map of concern. Additionally, we simulate real neuronal dynamics, introduce a glial cell-mediated Glial-LIF (Leaky Integrate-and-fire) model, and adjust multiple levels of BMUs to optimize the attention topological map.Experiments demonstrate that the proposed Self-organizing Glial Spiking Neural Network (SG-SNN) can generate attention topographies for dynamic event data from coarse to fine. A heuristic method based on cognitive science effectively guides the network's distribution of excitatory regions. Furthermore, the SG-SNN shows improved accuracy on three standard neuromorphic datasets: DVS128-Gesture, CIFAR10-DVS, and N-Caltech 101, with accuracy improvements of 0.3%, 2.4%, and 0.54% respectively. Notably, the recognition accuracy on the DVS128-Gesture dataset reaches 99.3%, achieving state-of-the-art (SOTA) performance.

Exploring temporal information dynamics in Spiking Neural Networks: Fast Temporal Efficient Training

BACKGROUND

Spiking Neural Networks (SNNs) hold significant potential in brain simulation and temporal data processing. While recent research has focused on developing neuron models and leveraging temporal dynamics to enhance performance, there is a lack of explicit studies on neuromorphic datasets. This research aims to address this question by exploring temporal information dynamics in SNNs.

NEW METHOD

To quantify the dynamics of temporal information during training, this study measures the Fisher information in SNNs trained on neuromorphic datasets. The information centroid is calculated to analyze the influence of key factors, such as the parameter k, on temporal information dynamics.

RESULTS

Experimental results reveal that the information centroid exhibits two distinct behaviors: stability and fluctuation. This study terms this phenomenon the Stable Information Centroid (SIC), which is closely related to the parameter k. Based on these findings, we propose the Fast Temporal Efficient Training (FTET) algorithm.

COMPARISON WITH EXISTING METHODS

Firstly, the method proposed in this paper does not require the introduction of additional complex training techniques. Secondly, it can reduce the computational load by 30% in the final 50 epochs. However, the drawback is the issue of slow convergence during the early stages of training.

CONCLUSION

This study reveals that the learning processes of SNNs vary across different datasets, providing new insights into the mechanisms of human brain learning. A limitation is the restricted sample size, focusing only on a few datasets and image classification tasks. The code is available at https://github.com/gtii123/fast-temporal-efficient-training.

Scaling Spike-Driven Transformer With Efficient Spike Firing Approximation Training

The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major challenges in realizing this vision: the performance gap between SNNs and ANNs, and the high training costs of SNNs. We identify intrinsic flaws in spiking neurons caused by binary firing mechanisms and propose a Spike Firing Approximation (SFA) method using integer training and spike-driven inference. This optimizes the spike firing pattern of spiking neurons, enhancing efficient training, reducing power consumption, improving performance, enabling easier scaling, and better utilizing neuromorphic chips. We also develop an efficient spike-driven Transformer architecture and a spike-masked autoencoder to prevent performance degradation during SNN scaling. On ImageNet-1k, we achieve state-of-the-art top-1 accuracy of 78.5%, 79.8%, 84.0%, and 86.2% with models containing 10 M, 19 M, 83 M, and 173 M parameters, respectively. For instance, the 10 M model outperforms the best existing SNN by 7.2% on ImageNet, with training time acceleration and inference energy efficiency improved by 4.5× and 3.9×, respectively. We validate the effectiveness and efficiency of the proposed method across various tasks, including object detection, semantic segmentation, and neuromorphic vision tasks. This work enables SNNs to match ANN performance while maintaining the low-power advantage, marking a significant step towards SNNs as a general visual backbone.

TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks

Spiking neural networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatiotemporal information representation ability. Given the critical role of attention mechanisms in enhancing neural network performance, the integration of SNNs and attention mechanisms exhibits tremendous potential to deliver energy-efficient and high-performance computing paradigms. In this article, we present a novel temporal-channel joint attention mechanism for SNNs, referred to as TCJA-SNN. The proposed TCJA-SNN framework can effectively assess the significance of spike sequence from both spatial and temporal dimensions. More specifically, our essential technical contribution lies on: 1) we employ the squeeze operation to compress the spike stream into an average matrix. Then, we leverage two local attention mechanisms based on efficient 1-D convolutions to facilitate comprehensive feature extraction at the temporal and channel levels independently and 2) we introduce the cross-convolutional fusion (CCF) layer as a novel approach to model the interdependencies between the temporal and channel scopes. This layer effectively breaks the independence of these two dimensions and enables the interaction between features. Experimental results demonstrate that the proposed TCJA-SNN outperforms the state-of-the-art (SOTA) on all standard static and neuromorphic datasets, including Fashion-MNIST, CIFAR10, CIFAR100, CIFAR10-DVS, N-Caltech 101, and DVS128 Gesture. Furthermore, we effectively apply the TCJA-SNN framework to image generation tasks by leveraging a variation autoencoder. To the best of our knowledge, this study is the first instance where the SNN-attention mechanism has been employed for high-level classification and low-level generation tasks. Our implementation codes are available at https://github.com/ridgerchu/TCJA.

A novel approach to enhancing biomedical signal recognition via hybrid high-order information bottleneck driven spiking neural networks

Biomedical signals, encapsulating vital physiological information, are pivotal in elucidating human traits and conditions, serving as a cornerstone for advancing human-machine interfaces. Nonetheless, the fidelity of biomedical signal interpretation is frequently compromised by pervasive noise sources such as skin, motion, and equipment interference, posing formidable challenges to precision recognition tasks. Concurrently, the burgeoning adoption of intelligent wearable devices illuminates a societal shift towards enhancing life and work through technological integration. This surge in popularity underscores the imperative for efficient, noise-resilient biomedical signal recognition methodologies, a quest that is both challenging and profoundly impactful. This study proposes a novel approach to enhancing biomedical signal recognition. The proposed approach employs a hierarchical information bottleneck mechanism within SNNs, quantifying the mutual information in different orders based on the depth of information flow in the network. Subsequently, these mutual information, together with the network's output and category labels, are restructured based on information theory principles to form the loss function used for training. A series of theoretical analyses and substantial experimental results have shown that this method can effectively compress noise in the data, and on the premise of low computational cost, it can also significantly outperform its vanilla counterpart in terms of classification performance.

Reconstruction of Adaptive Leaky Integrate-and-Fire Neuron to Enhance the Spiking Neural Networks Performance by Establishing Complex Dynamics

Since digital spiking signals can carry rich information and propagate with low computational consumption, spiking neural networks (SNNs) have received great attention from neuroscientists and are regarded as the future development object of neural networks. However, generating the appropriate spiking signals remains challenging, which is related to the dynamics property of neurons. Most existing studies imitate the biological neurons based on the correlation of synaptic input and output, but these models have only one time constant, thus ignoring the structural differentiation and versatility in biological neurons. In this article, we propose the reconstruction of adaptive leaky integrate-and-fire (R-ALIF) neuron to perform complex behaviors similar to real neurons. First, a synaptic cleft time constant is introduced into the membrane voltage charging equation to distinguish the leakage degree between the neuron membrane and the synaptic cleft, which can expand the representation space of spiking neurons to facilitate SNNs to obtain better information expression way. Second, R-ALIF constructs a voltage threshold adjustment equation to balance the firing rate of output signals. Third, three time constants are transformed into learnable parameters, enabling the adaptive adjustment of dynamics equation and enhancing the information expression ability of SNNs. Fourth, the computational graph of R-ALIF is optimized to improve the performance of SNNs. Moreover, we adopt a temporal dropout (TemDrop) method to solve the overfitting problem in SNNs and propose a data augmentation method for neuromorphic datasets. Finally, we evaluate our method on CIFAR10-DVS, ASL-DVS, and CIFAR-100, and achieve top1 accuracy of 81.0%, 99.8%, and 67.83%, respectively, with few time steps. We believe that our method will further promote the development of SNNs trained by spatiotemporal backpropagation (STBP).

Spiking Neural Networks with Adaptive Membrane Time Constant for Event-Based Tracking

The brain-inspired Spiking Neural Networks (SNNs) work in an event-driven manner and have an implicit recurrence in neuronal membrane potential to memorize information over time, which are inherently suitable to handle temporal event-based streams. Despite their temporal nature and recent approaches advancements, these methods have predominantly been assessed on event-based classification tasks. In this paper, we explore the utility of SNNs for event-based tracking tasks. Specifically, we propose a brain-inspired adaptive Leaky Integrate-and-Fire neuron (BA-LIF) that can adaptively adjust the membrane time constant according to the inputs, thereby accelerating the leakage of meaningless noise features and reducing the decay of valuable information. SNNs composed of our proposed BA-LIF neurons can achieve high performance without a careful and time-consuming trial-by-error initialization on the membrane time constant. The adaptive capability of our network is further improved by introducing an extra temporal feature aggregator (TFA) that assigns attention weights over the temporal dimension. Extensive experiments on various event-based tracking datasets validate the effectiveness of our proposed method. We further validate the generalization capability of our method by applying it to other event-classification tasks.

Enhancing SNN-based spatio-temporal learning: A benchmark dataset and Cross-Modality Attention model

Spiking Neural Networks (SNNs), renowned for their low power consumption, brain-inspired architecture, and spatio-temporal representation capabilities, have garnered considerable attention in recent years. Similar to Artificial Neural Networks (ANNs), high-quality benchmark datasets are of great importance to the advances of SNNs. However, our analysis indicates that many prevalent neuromorphic datasets lack strong temporal correlation, preventing SNNs from fully exploiting their spatio-temporal representation capabilities. Meanwhile, the integration of event and frame modalities offers more comprehensive visual spatio-temporal information. Yet, the SNN-based cross-modality fusion remains underexplored. In this work, we present a neuromorphic dataset called DVS-SLR that can better exploit the inherent spatio-temporal properties of SNNs. Compared to existing datasets, it offers advantages in terms of higher temporal correlation, larger scale, and more varied scenarios. In addition, our neuromorphic dataset contains corresponding frame data, which can be used for developing SNN-based fusion methods. By virtue of the dual-modal feature of the dataset, we propose a Cross-Modality Attention (CMA) based fusion method. The CMA model efficiently utilizes the unique advantages of each modality, allowing for SNNs to learn both temporal and spatial attention scores from the spatio-temporal features of event and frame modalities, subsequently allocating these scores across modalities to enhance their synergy. Experimental results demonstrate that our method not only improves recognition accuracy but also ensures robustness across diverse scenarios.

A Spatial-Channel-Temporal-Fused Attention for Spiking Neural Networks

Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing. As an essential factor for human perception, visual attention refers to the dynamic process for selecting salient regions in biological vision systems. Although visual attention mechanisms have achieved great success in computer vision applications, they are rarely introduced into SNNs. Inspired by experimental observations on predictive attentional remapping, we propose a new spatial-channel-temporal-fused attention (SCTFA) module that can guide SNNs to efficiently capture underlying target regions by utilizing accumulated historical spatial-channel information in the present study. Through a systematic evaluation on three event stream datasets (DVS Gesture, SL-Animals-DVS, and MNIST-DVS), we demonstrate that the SNN with the SCTFA module (SCTFA-SNN) not only significantly outperforms the baseline SNN (BL-SNN) and two other SNN models with degenerated attention modules, but also achieves competitive accuracy with the existing state-of-the-art (SOTA) methods. Additionally, our detailed analysis shows that the proposed SCTFA-SNN model has strong robustness to noise and outstanding stability when faced with incomplete data, while maintaining acceptable complexity and efficiency. Overall, these findings indicate that incorporating appropriate cognitive mechanisms of the brain may provide a promising approach to elevate the capabilities of SNNs.

Brain-inspired chaotic spiking backpropagation

Spiking neural networks (SNNs) have superior energy efficiency due to their spiking signal transmission, which mimics biological nervous systems, but they are difficult to train effectively. Although surrogate gradient-based methods offer a workable solution, trained SNNs frequently fall into local minima because they are still primarily based on gradient dynamics. Inspired by the chaotic dynamics in animal brain learning, we propose a chaotic spiking backpropagation (CSBP) method that introduces a loss function to generate brain-like chaotic dynamics and further takes advantage of the ergodic and pseudo-random nature to make SNN learning effective and robust. From a computational viewpoint, we found that CSBP significantly outperforms current state-of-the-art methods on both neuromorphic data sets (e.g. DVS-CIFAR10 and DVS-Gesture) and large-scale static data sets (e.g. CIFAR100 and ImageNet) in terms of accuracy and robustness. From a theoretical viewpoint, we show that the learning process of CSBP is initially chaotic, then subject to various bifurcations and eventually converges to gradient dynamics, consistently with the observation of animal brain activity. Our work provides a superior core tool for direct SNN training and offers new insights into understanding the learning process of a biological brain.

Exploiting noise as a resource for computation and learning in spiking neural networks

Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers.

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

Brain-inspired deep spiking neural network (DSNN) which emulates the function of the biological brain provides an effective approach for event-stream spatiotemporal perception (STP), especially for dynamic vision sensor (DVS) signals. However, there is a lack of generalized learning frameworks that can handle various spatiotemporal modalities beyond event-stream, such as video clips and 3D imaging data. To provide a unified design flow for generalized spatiotemporal processing (STP) and to investigate the capability of lightweight STP processing via brain-inspired neural dynamics, this study introduces a training platform called brain-inspired deep learning (BIDL). This framework constructs deep neural networks, which leverage neural dynamics for processing temporal information and ensures high-accuracy spatial processing via artificial neural network layers. We conducted experiments involving various types of data, including video information processing, DVS information processing, 3D medical imaging classification, and natural language processing. These experiments demonstrate the efficiency of the proposed method. Moreover, as a research framework for researchers in the fields of neuroscience and machine learning, BIDL facilitates the exploration of different neural models and enables global-local co-learning. For easily fitting to neuromorphic chips and GPUs, the framework incorporates several optimizations, including iteration representation, state-aware computational graph, and built-in neural functions. This study presents a user-friendly and efficient DSNN builder for lightweight STP applications and has the potential to drive future advancements in bio-inspired research.

Spiking neural network with working memory can integrate and rectify spatiotemporal features

In the real world, information is often correlated with each other in the time domain. Whether it can effectively make a decision according to the global information is the key indicator of information processing ability. Due to the discrete characteristics of spike trains and unique temporal dynamics, spiking neural networks (SNNs) show great potential in applications in ultra-low-power platforms and various temporal-related real-life tasks. However, the current SNNs can only focus on the information a short time before the current moment, its sensitivity in the time domain is limited. This problem affects the processing ability of SNN in different kinds of data, including static data and time-variant data, and reduces the application scenarios and scalability of SNN. In this work, we analyze the impact of such information loss and then integrate SNN with working memory inspired by recent neuroscience research. Specifically, we propose Spiking Neural Networks with Working Memory (SNNWM) to handle input spike trains segment by segment. On the one hand, this model can effectively increase SNN's ability to obtain global information. On the other hand, it can effectively reduce the information redundancy between adjacent time steps. Then, we provide simple methods to implement the proposed network architecture from the perspectives of biological plausibility and neuromorphic hardware friendly. Finally, we test the proposed method on static and sequential data sets, and the experimental results show that the proposed model can better process the whole spike train, and achieve state-of-the-art results in short time steps. This work investigates the contribution of introducing biologically inspired mechanisms, e.g., working memory, and multiple delayed synapses to SNNs, and provides a new perspective to design future SNNs.

STSC-SNN: Spatio-Temporal Synaptic Connection with temporal convolution and attention for spiking neural networks

Spiking neural networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological plausibility. The potential to efficiently extract spatio-temporal features makes it suitable for processing event streams. However, existing synaptic structures in SNNs are almost full-connections or spatial 2D convolution, neither of which can extract temporal dependencies adequately. In this work, we take inspiration from biological synapses and propose a Spatio-Temporal Synaptic Connection SNN (STSC-SNN) model to enhance the spatio-temporal receptive fields of synaptic connections, thereby establishing temporal dependencies across layers. Specifically, we incorporate temporal convolution and attention mechanisms to implement synaptic filtering and gating functions. We show that endowing synaptic models with temporal dependencies can improve the performance of SNNs on classification tasks. In addition, we investigate the impact of performance via varied spatial-temporal receptive fields and reevaluate the temporal modules in SNNs. Our approach is tested on neuromorphic datasets, including DVS128 Gesture (gesture recognition), N-MNIST, CIFAR10-DVS (image classification), and SHD (speech digit recognition). The results show that the proposed model outperforms the state-of-the-art accuracy on nearly all datasets.

ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

With event-driven algorithms, especially spiking neural networks (SNNs), achieving continuous improvement in neuromorphic vision processing, a more challenging event-stream dataset is urgently needed. However, it is well-known that creating an ES-dataset is a time-consuming and costly task with neuromorphic cameras like dynamic vision sensors (DVS). In this work, we propose a fast and effective algorithm termed Omnidirectional Discrete Gradient (ODG) to convert the popular computer vision dataset ILSVRC2012 into its event-stream (ES) version, generating about 1,300,000 frame-based images into ES-samples in 1,000 categories. In this way, we propose an ES-dataset called ES-ImageNet, which is dozens of times larger than other neuromorphic classification datasets at present and completely generated by the software. The ODG algorithm implements image motion to generate local value changes with discrete gradient information in different directions, providing a low-cost and high-speed method for converting frame-based images into event streams, along with Edge-Integral to reconstruct the high-quality images from event streams. Furthermore, we analyze the statistics of ES-ImageNet in multiple ways, and a performance benchmark of the dataset is also provided using both famous deep neural network algorithms and spiking neural network algorithms. We believe that this work shall provide a new large-scale benchmark dataset for SNNs and neuromorphic vision.