Learn Before
Concept

Steps of Fine-Tuning in Transfer Learning

Fine-tuning is a common technique in transfer learning that consists of four main steps. First, a neural network, known as the source model, is pre-trained on a large source dataset. Second, a target model is created by copying the architecture and parameters of the source model, excluding the output layer. The output layer is excluded because it is assumed to be closely related to the specific labels of the source dataset, making it inapplicable to the target dataset. Third, a new, randomly initialized output layer is added to the target model to match the number of categories in the target dataset. Finally, the target model is trained on the target dataset; the new output layer is trained from scratch while the parameters of the other layers are fine-tuned.

Image 0

0

2

Updated 2026-05-23

Tags

Data Science

Ch.1 Pre-training - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

D2L

Dive into Deep Learning @ D2L