Hands-On Transfer Learning with Python

Transfer bounds

Quantifying the transfer in transfer learning is also very important affecting about the quality of the transfer and its viability. To gauge the amount for the transfer, Hassan Mahmud and their co-authors used Kolmogorov complexity to prove certain theoretical bounds to analyze transfer learning and measure relatedness between tasks. Eaton and their co-authors presented a novel graph-based approach to measure knowledge transfer. Detailed discussions of these techniques are outside the scope of this book. Readers are encouraged to explore more on these topics using the publications outlined in this section.