Work

Transfer Learning using Neural Ordinary Differential Equations

Year: 2020

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2001.07342

Authors: S, Rajath, K, Sumukh Aithal, Subramanyam, Natarajan

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3001986309

Cites: 17

Cited by: 1

Related to: 10