06/26/2025, 08:05 AM UTC
微型设备中的小型化人工智能Artificial Intelligence in Miniature Format for Small Devices
➀ 格拉茨理工大学等机构的研究人员开发了可让AI模型在仅4KB内存的物联网设备上运行的技术，例如用于校准定位误差；
➁ 采用模块化专用模型、子空间可配置网络（SCN）、量化及剪枝等优化方法，在保证精度的同时降低计算资源需求；
➂ 应用场景涵盖工业自动化（无人机导航）、汽车安全（无钥匙门禁验证）和智能家居系统，显著延长设备电池续航。
➀ Researchers from TU Graz and partners developed methods to run AI models on IoT devices with ≤4KB memory, enabling localized AI processing for applications like precision positioning;
➁ Techniques include modular specialized models, subspace configurable networks (SCNs), quantization, and pruning to optimize efficiency while maintaining accuracy;
➂ Potential applications span industrial automation (drone navigation), automotive security (keyless entry verification), and smart home systems with extended battery life.
---
本文由大语言模型（LLM）生成，旨在为读者提供半导体新闻内容的知识扩展（Beta）。
