Presentation
Maximizing Energy Efficiency in Spiking Neural Networks: A Dynamic Joint Pruning Framework
DescriptionExisting pruning methods for Spiking Neural Networks (SNNs) focus on a single form of sparsity, overlooking the importance of joint pruning, which is critical for minimizing synaptic operations (SOPs) and enhancing energy efficiency. This paper presents a novel dynamic joint pruning framework that leverages both spatiotemporal spike sparsity and weight sparsity to minimize SOPs in SNN inference. The proposed framework integrates a multi-stage masking mechanism for fine-grained neuron firing threshold control, a Temporal Attention Batch Normalization (TABN) module with learnable time scaling factors, and a dynamic sparse strategy that adjusts importance coefficients based on real-time computational impact. Experimental results demonstrate that our method achieves maximum SOP reduction with minimal accuracy loss, establishing a new state-of-the-art in energy-efficient SNN pruning.
Event Type
Research Manuscript
TimeTuesday, June 2411:30am - 11:45am PDT
Location3001, Level 3
AI1: AI/ML Algorithms
Similar Presentations