2025· Neural Information Processing Systems· 1 citation· 44 references
Computer Science
TL;DR
This work proposes the use of ternary spike neurons, which enhance the information-carrying capacity in the spiking neural rendering model, and introduces Spik-NeRF (Spiking Neural Radi-ance Fields with Ternary Spike), which achieves rendering performance comparable to ANN-based NeRF models.
Abstract
Spiking Neural Networks (SNNs), as a biologically inspired neural network architecture, have garnered significant attention due to their exceptional energy efficiency and increasing potential for various applications. In this work, we extend the use of SNNs to neural rendering tasks and introduce Spik-NeRF (Spiking Neural Radi-ance Fields with Ternary Spike). We observe that the binary spike activation map of traditional SNNs lacks sufficient information capacity, leading to information loss and a subsequent decline in the performance of spiking neural rendering models. To address this limitation, we propose the use of ternary spike neurons, which enhance the information-carrying capacity in the spiking neural rendering model. With ternary spike neurons, Spik-NeRF achieves performance that is on par with, or nearly identical to, traditional ANN-based rendering models. Additionally, we present a re-parameterization technique for inference that allows Spik-NeRF with ternary spike neurons to retain the event-driven, multiplication-free advantages typical of binary spike neurons. Furthermore, to further boost the performance of Spik-NeRF, we employ a distillation method, using an ANN-based NeRF to guide the training of our Spik-NeRF model, which is more compatible with the our ternary neurons compared to the standard binary neurons and other neuron forms. We evaluate Spik-NeRF on both realistic and synthetic scenes, and the experimental results demonstrate that Spik-NeRF achieves rendering performance comparable to ANN-based NeRF models.
A Spiking Neural Network (SNN) is a kind of brain-inspired and event-driven network, which is becoming a promising energy-efficient alternative to Artificial Neural Networks (ANNs). In recent years, SNN methods have been successfully applied in the fields of electromagnetic signal processing and image signal processing, particularly in application scenarios that require low energy consumption. However, the performance of SNNs by direct training is far from satisfactory. In this paper, we study a novel learning method named SAD-SNN (Spatial-Activation Distillation for Spiking Neural Networks), which utilizes the ANN model to guide the SNN model learning. Unlike prior works that rely on element-wise feature alignment approaches, SAD-SNN aligns spatial-activation maps at different resolutions of the teacher and student networks. Specifically, we introduce a direct alignment approach, which defines a spatial-activation loss and normalizes the representation vectors of ANN and SNN, to alleviate the unexpected precision loss. This enables the knowledge of teacher ANNs to be effectively transferred to train student SNNs. On three image classification datasets, our proposed SAD-SNN outperforms other SNN training methods no matter whether homogeneous or heterogeneous teacher ANNs are used. Furthermore, we apply SAD-SNN to the electromagnetic signal detection task, demonstrating strong generalization ability and superior performance. In conclusion, the experimental results on various tasks and SNN architectures demonstrate that our method is a general and effective solution that significantly improves the learning of student SNNs with only two time steps.
Chongxiao Qu, Qian Zhang, Chenxiao Dou et al.· Italian National Conference...· 0 citations
Spiking neural networks (SNNs) have attracted growing interest due to their event-driven computation and close correspondence with biological neuronal signaling. Despite this, most SNN models focus exclusively on neuronal dynamics, overlooking the role of astrocytes—a major class of glial cells now recognized as active modulators of synaptic transmission, network excitability, and learning. In this work, an astrocyte-augmented SNN architecture is proposed by introducing a hidden layer of astrocytes that interact with excitatory neurons through gliotransmitter-mediated currents. The astrocytic dynamics are modeled using a simplified calcium-based framework derived from previous works, enabling efficient integration into spiking networks. Simulation results on an image classification task show that incorporating astrocytic modulation consistently enhances classification performance in leaky integrate-and-fire (LIF) networks, including under noisy conditions. These results suggest that augmenting simplified astrocytic dynamics can improve robustness and computational capability in SNNs, while also increasing their biological plausibility.
D. Garcia, Sabir Jacquir· International Conference on...· 0 citations
A central goal of current Spiking Neural Network (SNN) research is to improve their accuracy toward becoming low-power alternatives to Artificial Neural Networks (ANNs). This work further argues that realizing this ambition requires improving not only accuracy but also robustness, defined as the ability to maintain correct predictions under input perturbations. We identify two key issues in existing SNN methods that undermine robustness. First, binary spiking activations can produce large activation-state changes under small perturbations. Second, the lack of effective weight constraints makes network outputs more sensitive to input variations. To this end, we propose Burst Spiking Neural Networks (BuSNNs), built upon Burst-enhanced Spiking Neurons (BSNs) and a Dynamic Weight Constraint (DWC) mechanism. BSNs incorporate burst firing to provide a graded spiking pattern. This spiking mechanism mitigates perturbation-induced transitions in activation states and thereby enhances robustness. DWC penalizes connection weights based on activation states, effectively reducing weight magnitudes and improving robustness while preserving accuracy. We provide theoretical analyses to support these robustness effects. Experimental results further show that, on smaller-scale benchmarks such as CIFAR-10, BuSNNs outperform both SNN and ANN counterparts in accuracy and robustness. On large-scale ImageNet, BuSNN with the MS ResNet-34 backbone further improves top-1 accuracy and corruption robustness over the corresponding SNN baseline by 3.18% and 2.66%, respectively. Despite using spike-based activations, BuSNNs surpass 4-bit activation-quantized ANN baselines and approach 8-bit ANN baselines on ImageNet. They also preserve SNNs'low-power advantage. This work studies the accuracy-robustness problem in SNNs, advancing their practical viability in robust and energy-efficient applications.
Jiahong Zhang, Sijun Shen, Man Yao et al.· 0 citations
Spiking recurrent neural networks (SRNNs) rival gated recurrent neural networks (RNNs) on various tasks, yet they still lack several hallmarks of biological neural networks. We introduce a biologically grounded SRNN that implements Dale's law with conductance-based stands for a-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid (AMPA) and gamma-aminobutyric acid (GABA) reversal potentials. These reversal potentials modulate synaptic gain as a function of the postsynaptic membrane potential, and we derive theoretically how they make each neuron's effective dynamics and subthreshold resonance input-dependent. We trained SRNNs on the Spiking Heidelberg Digits (SHD) dataset and show that SRNNs with reversal potentials reduce spike energy by up to 3 × , while maintaining, or increasing, task accuracy. This leads to high-performing Dalean SRNNs that substantially improve on Dalean networks without reversal potentials. SRNNs with reversal potentials exhibited spike-train statistics closer to Poisson statistics, similar to biological neurons, and showed a substantial reduction in oscillatory activity, leading to increased heterogeneity in response properties. Thus, Dale's law with reversal potentials, a core feature of biological neural networks, can render SRNNs more accurate and energy-efficient.
Miguel Rodrigues, Carmen Gasco-Galvez, Martin A. Vinck· Frontiers in Computational N...· 0 citations
This work introduces a Temporal Feedback Coding (TFC) scheme that leverages feedback at the encoding stage to diversify spike patterns and designs a Global-Local Dynamic LIF (GLD-LIF) neuron that enhances cross-step dependency modeling by integrating local aggregation and global initialization.
The third generation of neural networks is called Spiking Neural Networks (SNNs) and presents an energy-efficient and physiologically realistic alternative to the traditional Artificial Neural Networks (ANNs). This review discusses the latest advances in SNN models, learning algorithms, and their implementation on neuromorphic hardware. Besides reinforcement learning techniques such as REINFORCE, supervised techniques, such as SpikeProp and unsupervised Spike-Timing-Dependent Plasticity (STDP), are considered in the context of reward-based learning. The performance of the neurological systems technologies, including the IBM TrueNorth, the FPGA-based, and the Intel Loihi, is checked. Despite significant improvement in parallel processing and energy usage in these systems, there are still problems with accuracy of the synapses, training complexity, and scalability. FPGA-based systems are promising in real-time processing, though they have programmability issues that limit their deployment. The article outlines the key limitation of SNN models, namely their inability to handle large datasets and difficult learning tasks. To advance the performance of neuromorphic systems, research is underway on hybrid SNN-ANN models and memristor-based synaptic storage. This review 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.
Mesala Sravani, K. Kumari, S. M. Reddy· International Journal of Unc...· 0 citations