arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.12416cs.LGcs.ARcs.ET
收藏

增强边缘端神经网络的可靠性:结合随机仿射变换的反向归一化

Enhancing Reliability of Neural Networks at the Edge: Inverted Normalization with Stochastic Affine Transformations

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Univ. Grenoble Alpes, CEA, CNRS, Grenoble INP, and IRIG-Spintec(格勒诺布尔阿尔卑斯大学、法国原子能委员会、法国国家科学研究中心、格勒诺布尔国立理工学院及IRIG-Spintec)

Soyed Tuhin Ahmed, Kamal Danouchi, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori

AI总结:

针对忆阻器存内计算中各类非理想因素导致的推理精度下降,提出结合随机仿射变换的新型归一化层,以增强边缘端 BayNN 的内在鲁棒性,最高提升精度 58.11%。

摘要:

贝叶斯神经网络(BayNNs)天然能够在预测中提供不确定性,因此成为安全关键应用中的合适选择。此外,利用基于忆阻器的存内计算(IMC)架构来实现它们,也使其能够用于资源受限的边缘应用。然而,除了预测不确定性之外,对计算噪声具备内在鲁棒性对于确保功能安全同样至关重要。特别是,基于忆阻器的 IMC 容易受到多种非理想因素的影响,例如制造偏差、运行时变化、漂移和失效,这些因素可能显著降低推理精度。本文提出一种方法,用于内在地增强部署在 IMC 架构中的 BayNN 的鲁棒性和推理精度。为此,我们引入了一种结合随机仿射变换的新型归一化层。在多个基准数据集上的实验结果表明,推理精度呈现平缓退化,最高提升达 58.11%。

英文摘要:

Bayesian Neural Networks (BayNNs) naturally provide uncertainty in their predictions, making them a suitable choice in safety-critical applications. Additionally, their realization using memristor-based in-memory computing (IMC) architectures enables them for resource-constrained edge applications. In addition to predictive uncertainty, however, the ability to be inherently robust to noise in computation is also essential to ensure functional safety. In particular, memristor-based IMCs are susceptible to various sources of non-idealities such as manufacturing and runtime variations, drift, and failure, which can significantly reduce inference accuracy. In this paper, we propose a method to inherently enhance the robustness and inference accuracy of BayNNs deployed in IMC architectures. To achieve this, we introduce a novel normalization layer combined with stochastic affine transformations. Empirical results in various benchmark datasets show a graceful degradation in inference accuracy, with an improvement of up to $58.11\%$.

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。

↑