Online Continual Learning for Embedded Devices
Online Continual Learning for Embedded Devices
复制标题
DOI：
10.48550/arxiv.2203.10681
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Tyler L. Hayes;Christopher Kanan
中科院分区：
文献类型：
--
作者：
Tyler L. Hayes;Christopher Kanan
家庭机器人、智能手机上的用户个性化以及增强/虚拟现实耳机等新应用需要实时设备上持续学习。然而，这种设置带来了独特的挑战：嵌入式设备的内存和计算能力有限，而传统的机器学习模型在非平稳数据流上更新时会遭受灾难性遗忘。虽然已经开发了几种在线持续学习模型，但它们对于嵌入式应用程序的有效性尚未得到严格研究。在本文中，我们首先确定在线持续学习者必须满足的标准才能有效地进行实时设备上学习。然后，我们研究了几种在线持续学习方法与移动神经网络一起使用时的功效。我们测量它们的性能、内存使用情况、计算要求以及泛化到域外输入的能力。
Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. However, this setting poses unique challenges: embedded devices have limited memory and compute capacity and conventional machine learning models suffer from catastrophic forgetting when updated on non-stationary data streams. While several online continual learning models have been developed, their effectiveness for embedded applications has not been rigorously studied. In this paper, we first identify criteria that online continual learners must meet to effectively perform real-time, on-device learning. We then study the efficacy of several online continual learning methods when used with mobile neural networks. We measure their performance, memory usage, compute requirements, and ability to generalize to out-of-domain inputs.