Transfer Learning vs. Domain Adaptation
Following quoted from Wikipedia
Domain adaptation is the ability to apply an algorithm trained in one or more “source domains” to a different (but related) “target domain”. Domain adaptation is a subcategory of transfer learning. In domain adaptation, the source and target domains all have the same feature space (but different distributions); in contrast, transfer learning includes cases where the target domain’s feature space is different from the source feature space or spaces.
Important Resources
- An Overview of Transfer Learning – Video lecture by Sinno Jialin Pan – Presentation by Sinno Jialin Pan et al.
- A Survey on Transfer Learning by Sinno Jialin Pan et al. – Paper
- Transfer Learning: Repurposing ML Algorithms from different domains to cloud defense – Presentation –
- Transfer Learning by Andrew Ng– Video Lecture
- An analysis of the transfer learning of convolutional neural networks for artistic images – Paper
- Book – Transfer Learning by Qiang Yang et al. – amazon.in
- How transferable are features in deep neural networks? by Yoshua Bengio et al. – paper
- Unsupervised Domain Adaptation by Backpropagation by Yaroslav Ganin et al. – paper
- Distilling the Knowledge in a Neural Network by Geoffrey Hinton et al. – paper