Description

The idea behind parameter-based methods is that a well-trained model on the source domain has learned a well-defined structure, and if two tasks are related, this structure can be transferred to the target model.

Technical Details

Relationships

Related Techniques

• D3A-IBTL Instance-based Transfer Learning (Unpublished)
• D3A-HBTL Hybrid-based Transfer Learning (Unpublished)
• D3A-SFTL Symmetric Feature-based Transfer Learning (Unpublished)
• D3A-HFBTL Heterogeneous Feature-based Transfer Learning (Unpublished)
• D3A-HTL Heterogeneous Transfer Learning (Unpublished)
• D3A-RBTL Relational-based Transfer Learning (Unpublished)
• D3A-AFTL Asymmetric Feature-based Transfer Learning (Unpublished)
• D3A-HAFBTL Heterogeneous Asymmetric Feature-based Transfer Learning (Unpublished)