English

Transfer Learning using Neural Ordinary Differential Equations

Machine Learning 2020-01-22 v1 Computer Vision and Pattern Recognition

Abstract

A concept of using Neural Ordinary Differential Equations(NODE) for Transfer Learning has been introduced. In this paper we use the EfficientNets to explore transfer learning on CIFAR-10 dataset. We use NODE for fine-tuning our model. Using NODE for fine tuning provides more stability during training and validation.These continuous depth blocks can also have a trade off between numerical precision and speed .Using Neural ODEs for transfer learning has resulted in much stable convergence of the loss function.

Keywords

Cite

@article{arxiv.2001.07342,
  title  = {Transfer Learning using Neural Ordinary Differential Equations},
  author = {Rajath S and Sumukh Aithal K and Natarajan Subramanyam},
  journal= {arXiv preprint arXiv:2001.07342},
  year   = {2020}
}
R2 v1 2026-06-23T13:16:06.313Z