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 2112.01675cs.LG
收藏

智能IoT系统的近似贝叶斯深度学习的挑战和机遇

Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems

Manning College of Information and Computer Sciences(马宁信息与计算机科学学院);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Meet P. Vadera, Benjamin M. Marlin

摘要:

近似贝叶斯深度学习方法对于解决在智能系统中部署深度学习组件时发生的几个问题具有重要的前景,包括减轻过度自信错误的发生并为分布外的示例提供增强的鲁棒性。然而,现有近似贝叶斯推理方法的计算要求可能使其不适合部署在包括低功耗边缘设备的智能物联网系统中。在本文中,我们提出了一系列用于监督式深度学习的近似贝叶斯推理方法,并强调了在当前边缘硬件上应用这些方法时面临的挑战和机遇。我们强调了几个潜在的解决方案,以减少模型的存储需求和提高计算的可扩展性,包括模型修剪和蒸馏方法。

英文摘要:

Approximate Bayesian deep learning methods hold significant promise for addressing several issues that occur when deploying deep learning components in intelligent systems, including mitigating the occurrence of over-confident errors and providing enhanced robustness to out of distribution examples. However, the computational requirements of existing approximate Bayesian inference methods can make them ill-suited for deployment in intelligent IoT systems that include lower-powered edge devices. In this paper, we present a range of approximate Bayesian inference methods for supervised deep learning and highlight the challenges and opportunities when applying these methods on current edge hardware. We highlight several potential solutions to decreasing model storage requirements and improving computational scalability, including model pruning and distillation methods.

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。

↑