7 papers
ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization
Kaiwen Tang, Di Yu, Jiaqi Zheng +4
Spiking neural networks (SNNs) are promising for edge sensing due to their event-driven computation and temporal filtering capability. However, standard leaky integrate-and-fire (L…
Optimizing High-Throughput Distributed Data Pipelines for Reproducible Deep Learning at Scale
Kashish Mittal, Di Yu, Roozbeh Ketabi +3
Training massive-scale deep learning models on datasets spanning tens of terabytes presents critical challenges in hardware utilization and training reproducibility. In this paper,…
Biologically Plausible Learning via Bidirectional Spike-Based Distillation
Changze Lv, Yifei Wang, Yanxun Zhang +7
Developing biologically plausible learning algorithms that can achieve performance comparable to error backpropagation remains a longstanding challenge. Existing approaches often c…
Edge Intelligence with Spiking Neural Networks
Shuiguang Deng, Di Yu, Changze Lv +10
The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditio…
ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks
Di Yu, Changze Lv, Xin Du +5
Most edge-cloud collaboration frameworks rely on the substantial computational and storage capabilities of cloud-based artificial neural networks (ANNs). However, this reliance res…
Dendritic Localized Learning: Toward Biologically Plausible Algorithm
Changze Lv, Jingwen Xu, Yiyang Lu +7
Backpropagation is the foundational algorithm for training neural networks and a key driver of deep learning's success. However, its biological plausibility has been challenged due…