Students of the Masters in Biomedical Informatics (MBI) and Bioinformatics and Integrative Genomics (BIG) PhD program at Harvard Medical School arrive from diverse range of academic backgrounds with similarly diverse experiences with machine learning. The outlined course intends to provide students with focused instruction on key deep learning concepts in linear algebra, computer science, statistics, data visualization, as well as general biomedical informatics methods and provide extensive hands-on experience with the relevant software systems.

Recent News

View all News


Deep learning is a subfield of machine learning that builds predictive models using large artificial neural networks. Deep learning has revolutionized the fields of computer vision, automatic speech recognition, natural language processing, and numerous areas of computational biology. In this class, we will introduce the basic concepts of deep neural networks and GPU computing, discuss convolutional neural networks and recurrent neural networks structures, and examine biomedical applications. Students are expected to be familiar with linear algebra and machine learning and will participate in a group deep learning project.

Learning Goals

  • Understand the state of the art deep learning algorithms
  • Understand the pros and cons of different approaches
  • Implement deep machine learning applications using cloud GPU servers
  • Become familiar with ways to optimize deep learning methods for biomedical applications
  • Appreciate the strengths and limitations of deep learning applications


Kun-Hsing (Kun) Yu
kun-hsing_yu@hms.harvard.edu   Website

Andrew Beam
Andrew_Beam@hms.harvard.edu   Website