Transfer Learning

machine-learning

Definition

Transfer Learning

Transfer learning is a paradigm where knowledge extracted from a source task in a source domain is applied to a different but related target task in a target domain . Formally, it aims to improve the learning of the target predictive function by leveraging parameters, features, or data distributions from and .

Methodological Benefits

Transfer learning is particularly effective when (e.g., training on synthetic images and testing on real-world photos) or when labelled data is scarce in the target domain. By utilising a pre-trained model as a starting point, it significantly reduces the computational resources and amount of target data required to achieve high performance.