Transfer learning works really well when you have limited data and when a network exists that solves a similar problem. You can use transfer learning to bring state-of-the art networks and giant volumes of data to an otherwise small problem. So, when should you use transfer learning? Anytime you can! But, there are two stipulations that I'd like you to think about first. We will discuss them in the following sections.
When transfer learning should be used
Get Deep Learning Quick Reference now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
