Transfer Learning using Neural Ordinary Differential Equations
This is an incremental improvement for machine learning practitioners seeking stable transfer learning methods.
The paper tackled the problem of transfer learning stability by using Neural Ordinary Differential Equations (NODE) for fine-tuning on the CIFAR-10 dataset with EfficientNets, resulting in more stable convergence of the loss function during training and validation.
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.