PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 28, 20240 citationsOpen Access

Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient

View Full Paper
YLYang LiFZFeifei ZhaoDZDongcheng Zhao

Key Points

Key points are not available for this paper at this time.

Abstract

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. The surrogate gradient (SG) algorithm has recently enabled spiking neural networks to shine in neuromorphic hardware. However, introducing surrogate gradients has caused SNNs to lose their original sparsity, thus leading to the potential performance loss. In this paper, we first analyze the current problem of direct training using SGs and then propose Masked Surrogate Gradients (MSGs) to balance the effectiveness of training and the sparseness of the gradient, thereby improving the generalization ability of SNNs. Moreover, we introduce a temporally weighted output (TWO) method to decode the network output, reinforcing the importance of correct timesteps. Extensive experiments on diverse network structures and datasets show that training with MSG and TWO surpasses the SOTA technique.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Li et al. (2024) studied this question.

synapsesocial.com/papers/68e62e92b6db6435875c05f7https://doi.org/10.48550/arxiv.2406.19645
Ask AI
Helpful
Bookmark
Share
View Full Paper