Transfer Learning Using the Minimum Description Length Principle with a Decision Tree Application

Transfer learning is about how learning from one domain or a collection of domains can be applied to another. It is learning from similarities and parallels, from experience. This paper is about a distribution free, data driven, extendable framework for transfer learning, based on the minimum description length principle. We define transfer learning in terms of a specific framework, where we have a collection of hypothesis from other application domains available, but not the data, a learning algorithm consistent over domains and a new, previously unseen learning task.