Presented By O’Reilly and Cloudera
Make Data Work
September 11, 2018: Training & Tutorials
September 12–13, 2018: Keynotes & Sessions
New York, NY

Democratizing deep learning with transfer learning

Lars Hulstaert (Microsoft)
11:20am–12:00pm Thursday, 09/13/2018
Data science and machine learning
Location: 1A 15/16 Level: Beginner
Secondary topics:  Deep Learning
Average rating: *****
(5.00, 1 rating)

Who is this presentation for?

  • Data scientists, consultants, data engineers, developers, and data professionals

Prerequisite knowledge

  • A basic understanding of data science and machine learning principles

What you'll learn

  • Understand transfer learning concepts and applications
  • Learn how to apply transfer learning to boost your NLP or CV pipelines


Transfer learning allows data scientists to leverage insights from large labeled datasets. The general idea of transfer learning is to use knowledge learned from tasks for which a lot of labeled data is available in settings where little labeled data is available. Transfer learning is not a machine learning model or technique; it is rather a design methodology within machine learning.

Lars Hulstaert explains what transfer learning is and how it can boost your NLP or CV pipelines. Lars offers an overview of transfer learning and explores the different levels of transfer learning, from multitask learning to pure feature-based learning. He then covers applications for NLP and CV. In the first, word embeddings are applied in a text classification problem. In the second, pretrained networks are applied in an object detection problem. Lars concludes by sharing a set of guidelines for enabling transfer learning in your problem domain.

Photo of Lars Hulstaert

Lars Hulstaert


Lars Hulstaert is a data scientist at Microsoft. Previously, he studied machine learning at Cambridge University and Ghent University.