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.
@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}
}