用SEKF仅用1%数据就能迁移神经网络模型，适合数据受限场景。
Using the SEKF to Transfer NN Models of Dynamical Systems with Limited Data
- 基于SEKF的模型迁移方法，利用少量新数据微调预训练模型。
- 仅需原始数据1%即可准确捕捉目标系统动态，误差小且计算开销低。
- 适用于数据稀缺或高成本的工程系统建模，如化工反应器、机械系统。
数据驱动的动力系统模型需要大量训练数据，但在许多实际应用中，由于成本或安全限制难以获取足够数据。本文提出使用子集扩展卡尔曼滤波器（SEKF）将预训练的神经网络模型适应到新的相似系统，仅需少量数据。在阻尼弹簧系统和连续搅拌釜反应器系统上的实验验证表明，对初始模型施加微小参数扰动，即可精准捕捉目标系统动态，所需数据量仅为原始训练数据的1%。此外，微调过程计算成本更低，且降低了泛化误差。
原文摘要 · Abstract (English)
Data-driven models of dynamical systems require extensive amounts of training data. For many practical applications, gathering sufficient data is not feasible due to cost or safety concerns. This work uses the Subset Extended Kalman Filter (SEKF) to adapt pre-trained neural network models to new, similar systems with limited data available. Experimental validation across damped spring and continuous stirred-tank reactor systems demonstrates that small parameter perturbations to the initial model capture target system dynamics while requiring as little as 1% of original training data. In addition, finetuning requires less computational cost and reduces generalization error.
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。