论文标题
面向性能的神经建筑搜索
Performance-Oriented Neural Architecture Search
论文作者
论文摘要
硬件软件共同设计是改善特定域计算系统性能的非常成功的策略。我们主张将相同方法应用于深度学习。具体而言，我们建议将神经体系结构搜索扩展到有关硬件的信息，以确保生产的模型设计除了准确性的典型标准外，还具有很高的效率。使用在边缘计算设备上音频中关键字发现的任务，我们证明了我们的方法导致神经体系结构不仅非常准确，而且还有效地映射到将执行推理的计算平台。使用我们修改的神经体系结构搜索，我们证明了$ 0.88 \％$的TOP-1准确性提高，$ 1.85 \ times $ $减少了嵌入式SOC中的关键字在音频中的关键字斑点，而高端GPU上的$ 1.59 \ times $。
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural architecture search with information about the hardware to ensure that the model designs produced are highly efficient in addition to the typical criteria around accuracy. Using the task of keyword spotting in audio on edge computing devices, we demonstrate that our approach results in neural architecture that is not only highly accurate, but also efficiently mapped to the computing platform which will perform the inference. Using our modified neural architecture search, we demonstrate $0.88\%$ increase in TOP-1 accuracy with $1.85\times$ reduction in latency for keyword spotting in audio on an embedded SoC, and $1.59\times$ on a high-end GPU.
