让微型设备在不支持浮点运算的情况下，用整数训练模型。
Tin-Tin: Towards Tiny Learning on Tiny Devices with Integer-based Neural Network Training
- 用整数重缩放技术管理动态范围，实现整数型权重更新。
- 在真实微型控制器上验证，支持低功耗持续学习应用。
- 适合资源极受限的嵌入式设备，如物联网传感器节点。
机器学习近年发展使其能在资源受限的边缘设备上部署，推动了智能环境感知等创新应用。然而，微控制器（MCUs）受限于内存、算力不足及缺乏专用浮点单元（FPUs），难以部署复杂机器学习模型，尤其难以支持持续学习能力。为此，我们提出 Tin-Tin，一种专为低功耗微控制器设计的基于整数的本地训练框架。Tin-Tin 引入新颖的整数重缩放技术，有效管理动态范围，并实现基于整数数据类型的高效权重更新。与针对带浮点单元、GPU 或 FPGA 设备优化的方法不同，Tin-Tin 针对微型 MCU 的独特需求，优先考虑能效和内存利用率。我们在真实微型设备上通过端到端应用实例验证了 Tin-Tin 的有效性，展示了其在边缘平台实现节能可持续机器学习应用的潜力。
原文摘要 · Abstract (English)
Recent advancements in machine learning (ML) have enabled its deployment on resource-constrained edge devices, fostering innovative applications such as intelligent environmental sensing. However, these devices, particularly microcontrollers (MCUs), face substantial challenges due to limited memory, computing capabilities, and the absence of dedicated floating-point units (FPUs). These constraints hinder the deployment of complex ML models, especially those requiring lifelong learning capabilities. To address these challenges, we propose Tin-Tin, an integer-based on-device training framework designed specifically for low-power MCUs. Tin-Tin introduces novel integer rescaling techniques to efficiently manage dynamic ranges and facilitate efficient weight updates using integer data types. Unlike existing methods optimized for devices with FPUs, GPUs, or FPGAs, Tin-Tin addresses the unique demands of tiny MCUs, prioritizing energy efficiency and optimized memory utilization. We validate the effectiveness of Tin-Tin through end-to-end application examples on real-world tiny devices, demonstrating its potential to support energy-efficient and sustainable ML applications on edge platforms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。