From The Harvard Business Review – using the recent Presidential Election & lack of data to illustrate Transfer Learning:

“a field that helps to solve these problems by offering a set of algorithms that identify the areas of knowledge which are “transferable” to the target domain. This broader set of data can then be used to help “train” the model. These algorithms identify the commonalities between the target task, recent tasks, previous tasks, and similar-but-not-the-same tasks. Thus, they help guide the algorithm to learn only from the relevant parts of the data.”


Dr. Jaime Carbonell, Professor of Computer Science – Carnegie Mellon University
“Proactive Learning and Structural Transfer Learning: Building Blocks of Cognitive Systems” (28min)

From InfoWorld

“Machine learning, once implemented, tends to be specific to the data and requirements of the task at hand. Transfer learning is the act of abstracting and reusing those smarts…” Read More


One thought on “Edu-Video | “Transfer Learning” — Reusing Your Machine Learning Results

  1. Great site you have here but I was wanting to know if you knew of
    any user discussion forums that cover the same topics talked about in this article?
    I’d really love to be a part of online community where I can get
    suggestions from other experienced people that share the same interest.
    If you have any recommendations, please let me know. Bless you!

Leave a Reply

Your email address will not be published.

Blog Publisher / Head of Data Science Search

Founder & Head of Data Science Search at Starbridge Partners, LLC.