Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912604066152448 |
|---|---|
| author | Cardoni, Matteo Leroux, Sam |
| author_facet | Cardoni, Matteo Leroux, Sam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20269 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation Cardoni, Matteo Leroux, Sam Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing 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. |
| title | Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation |
| topic | Machine Learning Computer Vision and Pattern Recognition Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2509.20269 |