Results 271 to 280 of about 6,675,279 (300)

Spiking Neural Network for Ultralow-Latency and High-Accurate Object Detection

IEEE Transactions on Neural Networks and Learning Systems, 2023
Spiking Neural Networks (SNNs) have attracted significant attention for their energy-efficient and brain-inspired event-driven properties. Recent advancements, notably Spiking-YOLO, have enabled SNNs to undertake advanced object detection tasks ...
Jinye Qu, Zeyu Gao, Tielin Zhang, Yan-Feng Lu, Huajin Tang, H. Qiao   +5 more
semanticscholar   +1 more source

Brain-Inspired Spiking Neural Network Using Superconducting Devices

IEEE Transactions on Emerging Topics in Computational Intelligence, 2023
Based on recent research in artificial neural networks, researchers have focused on topics from brain-like computing based on the Von Neumann architecture to brain-inspired computing based on the integration of storage and calculation due to the large ...
Huilin Zhang, Chen Gang, Chen Xu, Guoliang Gong, Huaxiang Lu   +4 more
semanticscholar   +1 more source

SNN-RAT: Robustness-enhanced Spiking Neural Network through Regularized Adversarial Training

Neural Information Processing Systems, 2022
Spiking neural networks (SNNs) are promising to be widely deployed in real-time and safety-critical applications with the advance of neuromorphic computing.
Jianhao Ding, Tong Bu, Zhaofei Yu, Tiejun Huang, Jian K. Liu   +4 more
semanticscholar   +1 more source

Energy efficient ECG classification with spiking neural network

Biomedical Signal Processing and Control, 2021
Heart disease is one of the top ten threats to global health in 2019 according to the WHO. Continuous monitoring of ECG on wearable devices can detect abnormality in the user’s heartbeat early, thereby significantly increasing the chance of early ...
Zhanglu Yan, Jun Zhou, W. Wong
semanticscholar   +1 more source

SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection

Neurocomputing
Underwater object detection is critical for oceanic research and industrial safety inspections. However, the complex optical environment and the limited resources of underwater equipment pose significant challenges to achieving high accuracy and low ...
Chenyang Li, Wenxuan Liu, Guo-Qiang Gong, Xiao-Bo Ding, Xian Zhong   +4 more
semanticscholar   +1 more source

Event-Based Multimodal Spiking Neural Network with Attention Mechanism

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2022
Human brain can effectively integrate visual and auditory information. Dynamic Vision Sensor (DVS) and Dynamic Audio Sensor (DAS) are event-based sensors imitating the mechanism of human retina and cochlea.
Qianhui Liu, Dong Xing, Lang Feng, Huajin Tang, Gang Pan   +4 more
semanticscholar   +1 more source

Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips

International Conference on Learning Representations
Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing.
Man Yao, Jia-Kui Hu, Tian-Xiang Hu, Yifan Xu, Zhaokun Zhou, Yong-Hong Tian, Bo-Xing Xu, Guo-Qi Li   +7 more
semanticscholar   +1 more source

Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection

European Conference on Computer Vision
Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are currently limited to simple classification tasks because of their poor performance. In this work,
Xin-Hao Luo, Man Yao, Yuhong Chou, Bo-Xing Xu, Guo-Qi Li   +4 more
semanticscholar   +1 more source

Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient

Neural Networks
Brain-inspired Spiking Neural Networks (SNNs) have attracted much attention due to their event-based computing and energy-efficient features. However, the spiking all-or-none nature has prevented direct training of SNNs for various applications.
Yang Li, Feifei Zhao, Dongcheng Zhao, Yi Zeng   +3 more
semanticscholar   +1 more source

Spiking Graph Neural Network on Riemannian Manifolds

Neural Information Processing Systems
Graph neural networks (GNNs) have become the dominant solution for learning on graphs, the typical non-Euclidean structures. Conventional GNNs, constructed with the Artificial Neuron Network (ANN), have achieved impressive performance at the cost of high
Li Sun, Zhenhao Huang, Qiqi Wan, Hao Peng, Philip S. Yu   +4 more
semanticscholar   +1 more source