U.S. flag

An official website of the United States government

June 11: Demystifying Deep Learning—A Practical Approach in MATLAB

On June 11, the NIH Library will host a two-part MATLAB training featuring a demonstration of deep learning methods followed by a hands-on session. The class will be held in the NIH Library Training Room in Building 10.

  • 10:00 a.m.–12:00 p.m.:  MATLAB Demonstration
  • 1:00–2:00 p.m.:  MATLAB Hands-on Session

Registration is available now on the NIH Library website.

The MATLAB deep learning method can achieve state-of-the-art accuracy in many human-like tasks such as naming objects in a scene or recognizing optimal paths in an environment. To implement deep learning, researchers need to assemble large data sets and then build a neural network to train, visualize, and evaluate different models. This often requires specialized hardware and unique programming knowledge.

In these training sessions, new MATLAB features that simplify these tasks and eliminate low-level programming will be demonstrated. The instructors will share practical knowledge of the domain of deep learning and guide you through building and training neural networks that recognize handwriting and classify food in a scene. 

You will also learn MATLAB features that allow you to:

  • Manage extremely large sets of images
  • Perform classification and pixel-level semantic segmentation on images
  • Import training data sets from networks such as GoogLeNet
  • Automatically convert a model to CUDA to run on GPUs

For questions and more information, please contact Doug Joubert at the NIH Library:  douglas.joubert@nih.gov

The NIH Library in Building 10 serves the information needs of NIH staff and select Department of Health and Human Services (HHS) agencies. The NIH Library is part of the Office of Research Services (ORS) in the Office of the Director (OD).​​NIH Library classes, events, resources, and services, subscribe to our e-news