Transfer learning

Last updated Nov 14, 2024 Edit Source

Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem

See:

• AI/Multi-task learning
• AI/Generative AI/Foundation models

• https://en.wikipedia.org/wiki/Transfer_learning
• https://github.com/artix41/awesome-transfer-learning
• Transfer Learning - Machine Learning’s Next Frontier
• Domain adaptation
  • Domain adaptation is a field associated with machine learning and transfer learning. This scenario arises when we aim at learning from a source data distribution a well performing model on a different (but related) target data distribution
• Fine-tuning with Keras and Deep Learning

• #COURSE Transfer Learning | Kaggle

• #CODE pytorch-adapt
  • Domain adaptation made easy. Fully featured, modular, and customizable
  • https://kevinmusgrave.github.io/pytorch-adapt/
• #CODE TLlib
  • open-source and well-documented library for Transfer Learning. It is based on pure PyTorch with high performance and friendly API
• #code Salad
  • https://domainadaptation.org/
• #code Robustness
  • https://domainadaptation.org/robusta/

• #PAPER A Brief Review of Domain Adaptation (Farahani 2020)