arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.08970cs.LG
收藏

用于高效始终在线模型的门控压缩层

Gated Compression Layers for Efficient Always-On Models

Google LLC(谷歌有限责任公司)

Haiguang Li, Trausti Thormundsson, Ivan Poupyrev, Nicholas Gillian

摘要:

移动和嵌入式机器学习开发人员经常不得不在两种较差的设备上部署策略之间进行妥协:牺牲准确性并积极缩小其模型以在专用低功耗内核上运行;或者通过在更强大的计算内核(如神经处理单元或主应用处理器)上运行更大的模型来牺牲电池。在本文中,我们提出了一种新的门控压缩层,可用于将现有的神经网络架构转换为门控神经网络。门控神经网络具有多个特性,非常适合设备上的用例,有助于显著降低功耗、提高准确性并利用异构计算核心。我们提供了五个公共图像和音频数据集的结果,这些数据集证明了所提出的门控压缩层可以有效地阻止高达96%的负样本,压缩97%的正样本,同时保持或提高模型的准确性。

英文摘要:

Mobile and embedded machine learning developers frequently have to compromise between two inferior on-device deployment strategies: sacrifice accuracy and aggressively shrink their models to run on dedicated low-power cores; or sacrifice battery by running larger models on more powerful compute cores such as neural processing units or the main application processor. In this paper, we propose a novel Gated Compression layer that can be applied to transform existing neural network architectures into Gated Neural Networks. Gated Neural Networks have multiple properties that excel for on-device use cases that help significantly reduce power, boost accuracy, and take advantage of heterogeneous compute cores. We provide results across five public image and audio datasets that demonstrate the proposed Gated Compression layer effectively stops up to 96% of negative samples, compresses 97% of positive samples, while maintaining or improving model 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。

↑