arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.12445cs.NEcs.LG
收藏

通过注意力引导压缩实现低延迟节能深度SNN

Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression

University of Southern California(南加州大学)

Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel

摘要:

深度脉冲神经网络(SNN)已经成为传统深度学习框架的潜在替代方案,因为它们有望在事件驱动的神经形态硬件上提供更高的计算效率。然而,为了在复杂的视觉应用中表现良好,大多数SNN训练框架都会产生较大的推理延迟,这会导致尖峰活动增加和能量效率降低。因此,最大限度地减少平均尖峰活动,同时保持精度深SNNs仍然是一个重大的挑战和机遇。本文提出了一种非迭代SNN训练技术,实现超高压缩,减少尖峰活动,同时保持高推理精度。特别是,我们的框架首先使用未压缩的元模型的注意力映射来产生压缩的ANN。可以调整此步骤以支持不规则和结构化通道修剪,从而在广泛的平台上利用计算优势。然后,该框架使用直接输入执行基于稀疏学习的监督SNN训练。在训练过程中,它联合优化SNN权重、阈值和泄漏参数,以在保持压缩的同时最大限度地减少所需的时间步长。为了评估我们的方法的优点,我们在CIFAR-10和CIFAR-100上使用VGG和ResNet的变体进行了实验,并在Tiny-ImageNet上使用VGG 16进行了实验。通过所提出的技术生成的SNN模型产生的SOTA压缩比高达33.4倍,与基线未修剪的模型相比,准确度没有显着下降。与现有的SNN修剪方法相比,我们实现了高达8.3倍的压缩,提高了准确性。

英文摘要:

Deep spiking neural networks (SNNs) have emerged as a potential alternative to traditional deep learning frameworks, due to their promise to provide increased compute efficiency on event-driven neuromorphic hardware. However, to perform well on complex vision applications, most SNN training frameworks yield large inference latency which translates to increased spike activity and reduced energy efficiency. Hence,minimizing average spike activity while preserving accuracy indeep SNNs remains a significant challenge and opportunity.This paper presents a non-iterative SNN training technique thatachieves ultra-high compression with reduced spiking activitywhile maintaining high inference accuracy. In particular, our framework first uses the attention-maps of an un compressed meta-model to yield compressed ANNs. This step can be tuned to support both irregular and structured channel pruning to leverage computational benefits over a broad range of platforms. The framework then performs sparse-learning-based supervised SNN training using direct inputs. During the training, it jointly optimizes the SNN weight, threshold, and leak parameters to drastically minimize the number of time steps required while retaining compression. To evaluate the merits of our approach, we performed experiments with variants of VGG and ResNet, on both CIFAR-10 and CIFAR-100, and VGG16 on Tiny-ImageNet.The SNN models generated through the proposed technique yield SOTA compression ratios of up to 33.4x with no significant drops in accuracy compared to baseline unpruned counterparts. Compared to existing SNN pruning methods, we achieve up to 8.3x higher compression with improved accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑