Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches (NAS) that improve the chance of success in practical situations. Our search simultaneously optimizes for network accuracy, energy efficiency and memory usage. We benchmark the performance of our search on real hardware, but since running thousands of tests with real hardware is difficult we use a random forest model to roughly predict the energy usage of a candidate network. We present a search strategy that uses both Bayesian and regularized evolutionary search with particle swarms, and employs early-stopping to reduce the computational burden. Our search, evaluated on a sound-event classification dataset based upon AudioSet, results in an order of magnitude less energy per inference and a much smaller memory footprint than our baseline MobileNetV1/V2 implementations while slightly improving task accuracy. We also demonstrate how combining a 2D spectrogram with a convolution with many filters causes a computational bottleneck for audio classification and that alternative approaches reduce the computational burden but sacrifice task accuracy.

翻译：移动和边缘计算设备在常开分类任务中需要能量高效的神经网络架构。本文提出了神经架构搜索（NAS）的多项改进，以提升其在实际场景中的成功概率。我们的搜索同时优化网络精度、能量效率和内存占用。我们在真实硬件上对搜索性能进行基准测试，但鉴于在真实硬件上运行数千次测试存在困难，因此采用随机森林模型粗略预测候选网络的能量消耗。我们提出一种结合贝叶斯搜索、正则化进化搜索与粒子群优化的策略，并采用早停法降低计算负担。基于AudioSet的声音事件分类数据集评估表明，与基线MobileNetV1/V2实现相比，我们的搜索在略微提升任务精度的同时，每次推理能耗降低一个数量级，内存占用也大幅减小。我们还证明了将二维频谱图与多滤波器卷积相结合会导致音频分类的计算瓶颈，而替代方案虽能减轻计算负担却牺牲了任务精度。