Deep Learning has celebrated resounding successes in many application areas of relevance to the Internet-of-Things, for example, computer vision and machine listening. To fully harness the power of deep leaning for the IoT, these technologies must ultimately be brought directly to the edge. The obvious challenge is that deep learning techniques can only be implemented on strictly resource-constrained edge devices if the models are radically downsized. This task relies on different model compression techniques, such as network pruning, quantization and the recent advancement of XNOR-Net. This paper examines the suitability of these techniques for audio classification in microcontrollers. We present an XNOR-Net for end-to-end raw audio classification and a comprehensive empirical study comparing this approach with pruning-and-quantization methods. We show that raw audio classification with XNOR yields comparable performance to regular full precision networks for small numbers of classes while reducing memory requirements 32-fold and computation requirements 58-fold. However, as the number of classes increases significantly, performance degrades and pruning-and-quantization based compression techniques take over as the preferred technique being able to satisfy the same space constraints but requiring about 8x more computation. We show that these insights are consistent between raw audio classification and image classification using standard benchmark sets.To the best of our knowledge, this is the first study applying XNOR to end-to-end audio classification and evaluating it in the context of alternative techniques. All code is publicly available on GitHub.
翻译:深层次的学习技术在与互联网相关许多应用领域取得了巨大成功,例如计算机视觉和机器监听等。为了充分利用深度倾斜IOT的力量,这些技术最终必须直接带到边缘。显而易见的挑战是,深层次的学习技术只能在严格资源限制的边缘设备上实施,如果模型大幅缩小,那么深层次的学习技术只能在严格的资源限制的边缘设备上实施。这项任务依赖于不同的模型压缩技术,例如网络剪裁、定量化和XNOR-Net的最近进步。本文审查了这些技术在微控制器音频分类中的适宜性。我们为终端对终端对终端原始音频分类提供了一个 XNOR-Net,并将这一全面的经验性研究与裁剪裁方法进行比较。我们显示,与XNOR的原始音频分类的原始性能可与固定的完全精密网络相比,同时减少记忆要求32倍和计算要求58倍。然而,随着班级数量的大量增加,业绩退化和基于压缩技术的运行和裁剪辑作为首选的替代技术被取代。我们提出的最终技术,能够对原始的图像进行同样的精确的分类,我们需要这些精确的精确的计算。我们用最精确的精确的分类来进行最精确的计算。