5 papers
Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses
Wuque Cai, Hongze Sun, Quan Tang +6
Spiking neural networks (SNNs) are promising for neuromorphic computing, but high-performing models still rely on dense multilayer architectures with substantial communication and…
Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation
Hongze Sun, Wuque Cai, Duo Chen +7
As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks.…
A Brain-to-Population Graph Learning Framework for Diagnosing Brain Disorders
Qianqian Liao, Wuque Cai, Hongze Sun +4
Recent developed graph-based methods for diagnosing brain disorders using functional connectivity highly rely on predefined brain atlases, but overlook the rich information embedde…
NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
Wuque Cai, Hongze Sun, Jiayi He +5
Spiking neural networks (SNNs) are artificial neural networks based on simulated biological neurons and have attracted much attention in recent artificial intelligence technology s…
ST-FlowNet: An Efficient Spiking Neural Network for Event-Based Optical Flow Estimation
Hongze Sun, Jun Wang, Wuque Cai +6
Spiking Neural Networks (SNNs) have emerged as a promising tool for event-based optical flow estimation tasks due to their ability to leverage spatio-temporal information and low-p…