Aug 2024· IEEE Transactions on Neural Networks and Learning Systems· Vol PP· 16 citations· ⚡ 4 influential
Computer ScienceMedicine
TL;DR
The proposed parallel multi-compartment spiking neuron (PMSN) presents a promising solution to harness the computational advantages of detailed biological neurons, enabling high-performance and efficient temporal processing on neuromorphic computing systems.
Abstract
Spiking neural networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multiscale temporal processing compared to their biological counterparts. This limitation has resulted in poor performance in many pattern recognition tasks with information that varies across different timescales. To address this issue, we put forward a novel spiking neuron model called the parallel multi-compartment spiking neuron (PMSN). The PMSN emulates biological neurons by incorporating multiple interacting substructures and allows for flexible adjustment of the substructure counts to effectively represent temporal information across diverse timescales. In addition, to address the computational burden associated with the increased complexity of the proposed model, we introduce two parallelization techniques that decouple the temporal dependencies of neuronal updates, enabling parallelized training across different time steps. Our experiments across a wide range of pattern recognition tasks demonstrate that PMSN outperforms state-of-the-art (SOTA) spiking neuron models in temporal processing capacity and training speed. Specifically, compared with the commonly used leaky integrate-and-fire (LIF) neuron, PMSN offers more than $10\times $ acceleration and a 30% accuracy improvement on the Sequential CIFAR-10 dataset while maintaining comparable computational cost. Our implementation on neuromorphic hardware further demonstrates the deployability of PMSN and highlights its favorable tradeoff between effectiveness and efficiency. Therefore, the proposed PMSN presents a promising solution to harness the computational advantages of detailed biological neurons, enabling high-performance and efficient temporal processing on neuromorphic computing systems. Code is available at https://github.com/xychen-comp/PMSN.
This work proposes a noisy group neuron (NGN) model, which incorporates population-level synchronous resetting and neural stochasticity as fundamental computational mechanisms, and develops the NGN method as a framework that combines the NGN model with backpropagation learning based on mean-field dynamics.
Yajie Zhai, Yanmei Kang, Meng Li et al.· 0 citations
Spiking neural networks (SNNs) have garnered significant attention in reinforcement learning tasks for their low power consumption. However, traditional spiking reinforcement learning (SRL) methods, which rely on local-connected encoding and fixed-threshold learning, struggle to capture the inter-dimensional correlations of input information within short timesteps, limiting the network’s expressive capacity at low timesteps. While increasing timesteps can significantly enhance performance, excessive timesteps result in substantial delays. To address this contradiction and enhance the expressive and decision-making capabilities of SNNs within short timesteps, we propose Mask-Adaptive Global Connection (MAGC), a novel encoding method that efficiently captures long-range dependencies via sparse, adaptively masked connections—enabling global feature interaction in a single timestep. Additionally, dynamic-threshold spiking neurons are introduced to effectively capture and distinguish subtle changes in input signals at each timestep, thereby enhancing the spatial-temporal state representation during spike information transmission. Extensive experimental results demonstrate that the proposed method achieves performance comparable to state-of-the-art algorithms using only a single timestep, while significantly reducing inference latency and energy consumption. When extended to multiple timesteps, our approach consistently outperforms existing methods, showing substantial improvements across eight continuous control tasks from OpenAI Gym.
Rong Xiao, Zhiyuan Hu, Ping He et al.· IEEE Transactions on Image P...· 0 citations
It is aimed at proving that SNNs have potential in such areas as computer vision, robotics, and speech recognition, and their role in overcoming the barrier between artificial and biological neural systems is proved.
Mesala Sravani, K. Kumari, S. M. Reddy· International Journal of Unc...· 0 citations
While neuromorphic systems offer a promising path for processing dynamic, event-based data, current benchmarks often fail to isolate the specific impact of temporal integration on model performance. To address this, our research rigorously investigates how neuromorphic architectures encode and integrate temporal information by conducting a comprehensive ablation study using a hybrid network. We systematically transition from a fully spatial Convolutional Neural Network (CNN) to a fully Spiking Neural Network (SNN) by progressively replacing ReLU activations with spiking neurons across nine distinct model configurations. To challenge these architectures, we introduce the Temporal-ASL Dataset, a neuromorphic benchmark specifically curated with signs that exhibit high spatial isomorphism but distinct temporal signatures. This approach allows us to decouple spatial features from motion dynamics and quantify the marginal contribution of spiking membrane dynamics in resolving ambiguities that remain invisible to frame-isolated models. Our analysis reveals a performance hierarchy that peaks at 72.5% with a hybrid SNN configuration, representing a 6.25% improvement over the spatial CNN baseline. Logit trajectory analysis confirms this boost stems from the spiking layers’ ability to disambiguate spatially similar signs. However, accuracy declines steadily in deeper hierarchies, falling to 23.75% for the fully spiking SNN. Ultimately, these findings demonstrate that shallow neuromorphic integration effectively maximizes the gains from temporal integration while mitigating the information loss inherent in binary spike quantization.
J. Seekings, Peyton S. Chandarana, Arshia Eslami et al.· International Conference on...· 0 citations
This work proposes Burst Spiking Neural Networks (BuSNNs), built upon Burst-enhanced Spiking Neurons and a Dynamic Weight Constraint (DWC) mechanism, which mitigates perturbation-induced transitions in activation states and thereby enhances robustness.
Jiahong Zhang, Sijun Shen, Man Yao et al.· 0 citations
Phenomenological spiking neuron models such as Izhikevich, adaptive quadratic integrate-and-fire (aQIF), and Adaptive Exponential (AdEx) are widely used because of their simplicity and numerical efficiency. These models reproduce diverse neuronal dynamics through a slow self-inhibitory adaptation variable. Here we introduce their symmetric counterpart by replacing adaptation with slow self-excitation, motivated by intrinsic calcium-mediated membrane currents. This minimal modification enables robust persistent spiking and working-memory dynamics without compromising computational efficiency. These properties remain in excitatory spiking neural networks. We then derive and validate a mean-field neural mass model that remains stable while retaining working-memory functionality. Additionally, we implement the single-neuron model in a minimal memristor-based neuromorphic circuit and experimentally confirm its dynamics. These results provide scalable tools for large-scale brain simulations and neuromorphic applications in robotics, brain-machine interfaces, and edge AI devices.
D. Depannemaecker, Adrien D’hollande, G. Casagrande et al.· Nature Communications· 0 citations
