FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks
FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks
Spiking Neural Networks (SNNs) offer a biologically plausible framework for energy-efficient neuromorphic computing. However, it is a challenge to train SNNs due to their non-differentiability, efficiently. Existing gradient approximation approaches frequently sacrifice accuracy and face deployment limitations on edge devices due to the substantial computational requirements of backpropagation. To address these challenges, we propose a Forward-Forward (FF) based gradient approximation-free training framework for Spiking Neural Networks, which treats spiking activations as black-box modules, thereby eliminating the need for gradient approximation while significantly reducing computational complexity. Furthermore, we introduce a class-aware complexity adaptation mechanism that dynamically optimizes the loss function based on inter-class difficulty metrics, enabling efficient allocation of network resources across different categories. Experimental results demonstrate that our proposed training framework achieves test accuracies of 99.58%, 92.13%, and 75.64% on the MNIST, Fashion-MNIST, and CIFAR-10 datasets, respectively, surpassing all existing FF-based SNN approaches. Additionally, our proposed method exhibits significant advantages in terms of memory access and computational power consumption.
Changqing Xu、Ziqiang Yang、Yi Liu、Xinfang Liao、Guiqi Mo、Hao Zeng、Yintang Yang
计算技术、计算机技术
Changqing Xu,Ziqiang Yang,Yi Liu,Xinfang Liao,Guiqi Mo,Hao Zeng,Yintang Yang.FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks[EB/OL].(2025-08-01)[2025-08-07].https://arxiv.org/abs/2507.23643.点此复制
评论