Direct training high-performance deep spiking neural networks: a review of theories and methods

C Zhou, H Zhang, L Yu, Y Ye, Z Zhou… - Frontiers in …, 2024 - frontiersin.org
Spiking neural networks (SNNs) offer a promising energy-efficient alternative to artificial
neural networks (ANNs), in virtue of their high biological plausibility, rich spatial-temporal …

Brain-inspired computing: A systematic survey and future trends

G Li, L Deng, H Tang, G Pan, Y Tian… - Proceedings of the …, 2024 - ieeexplore.ieee.org
Brain-inspired computing (BIC) is an emerging research field that aims to build fundamental
theories, models, hardware architectures, and application systems toward more general …

Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection

X Luo, M Yao, Y Chou, B Xu, G Li - European Conference on Computer …, 2024 - Springer
Abstract Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-
power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are …

Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions

Y Hu, Q Zheng, G Li, H Tang, G Pan - arxiv preprint arxiv:2409.02111, 2024 - arxiv.org
Deep learning has revolutionized artificial intelligence (AI), achieving remarkable progress
in fields such as computer vision, speech recognition, and natural language processing …

Scaling spike-driven transformer with efficient spike firing approximation training

M Yao, X Qiu, T Hu, J Hu, Y Chou… - … on Pattern Analysis …, 2025 - ieeexplore.ieee.org
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 …

MetaLA: Unified optimal linear approximation to softmax attention map

Y Chou, M Yao, K Wang, Y Pan, R Zhu, Y Zhong… - arxiv preprint arxiv …, 2024 - arxiv.org
Various linear complexity models, such as Linear Transformer (LinFormer), State Space
Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional …

RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding

K Wu, M Yao, Y Chou, X Qiu, R Yang, B Xu… - Proceedings of the 32nd …, 2024 - dl.acm.org
Spiking Neural Networks (SNNs) have received widespread attention due to their unique
neuronal dynamics and low-power nature. Previous research empirically shows that SNNs …

BKDSNN: Enhancing the Performance of Learning-Based Spiking Neural Networks Training with Blurred Knowledge Distillation

Z Xu, K You, Q Guo, X Wang, Z He - European Conference on Computer …, 2024 - Springer
Spiking neural networks (SNNs), which mimic biological neural systems to convey
information via discrete spikes, are well-known as brain-inspired models with excellent …

Ternary spike-based neuromorphic signal processing system

S Wang, D Zhang, A Belatreche, Y **ao, H Qing… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep Neural Networks (DNNs) have been successfully implemented across various signal
processing fields, resulting in significant enhancements in performance. However, DNNs …

SVFormer: a direct training spiking transformer for efficient video action recognition

L Yu, L Huang, C Zhou, H Zhang, Z Ma, H Zhou… - arxiv preprint arxiv …, 2024 - arxiv.org
Video action recognition (VAR) plays crucial roles in various domains such as surveillance,
healthcare, and industrial automation, making it highly significant for the society …