Transfer learning
Learning in humans is a continuous process—whatever we learn today is built upon the learning we have had in the past. For example, if you know how to drive a bicycle, you can extend the same knowledge to drive a motorcycle, or drive a car. The driving rule remains the same—the only thing that changes is the control panel and actuators. However, in deep learning, we often start afresh. Is it possible to use the knowledge the model has gained in solving a problem in one domain, to solve the problem in another related domain?
Yes, it's indeed possible, and it's called transfer learning. Though a lot of research is still going on in the field, a great deal of success has been achieved in applying transfer learning in the area ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access