用预测编码+反向传播混合训练，让模型在设备端高效适应环境变化。
Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation
- 先用反向传播预训练，再用预测编码在线微调。
- 在MNIST和CIFAR-10上实现低开销的域适应，恢复因分布偏移损失的准确率。
- 适合边缘设备或类脑芯片，兼顾性能与计算效率。
随着深度神经网络在动态真实环境中的广泛应用，单一静态模型往往难以应对。传感器漂移或光照变化导致的输入数据分布改变，需要持续模型适应。本文提出一种混合训练方法，结合反向传播与预测编码的优势，实现高效的设备端域适应。首先使用反向传播离线训练深度神经网络，获得高初始性能；随后采用预测编码进行在线适应，使模型能恢复因输入分布变化而丢失的准确率。该方法利用反向传播在表征学习上的鲁棒性，以及预测编码在持续学习中的计算高效性，特别适用于资源受限的边缘设备或未来的类脑加速器。在MNIST和CIFAR-10数据集上的实验表明，该混合策略能在较低计算开销下实现有效适应，为动态环境中维持模型性能提供了有前景的解决方案。
原文摘要 · Abstract (English)
As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate continual model adaptation. In this paper, we propose a hybrid training methodology that enables efficient on-device domain adaptation by combining the strengths of Backpropagation and Predictive Coding. The method begins with a deep neural network trained offline using Backpropagation to achieve high initial performance. Subsequently, Predictive Coding is employed for online adaptation, allowing the model to recover accuracy lost due to shifts in the input data distribution. This approach leverages the robustness of Backpropagation for initial representation learning and the computational efficiency of Predictive Coding for continual learning, making it particularly well-suited for resource-constrained edge devices or future neuromorphic accelerators. Experimental results on the MNIST and CIFAR-10 datasets demonstrate that this hybrid strategy enables effective adaptation with a reduced computational overhead, offering a promising solution for maintaining model performance in dynamic environments.
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。