Demystifying Deep Learning: A Practical Approach in MATLAB

  • Registration Closed
  • Jun 11, 2018
  • 10:00 AM to 02:00 PM
  • NIH Library Training Room

Session Description

Are you new to deep learning and want to learn how to use it in your work?   Deep learning 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; then build a neural network, to train, visualize, and evaluate different models – sometimes using specialized hardware, and typically requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.

In these sessions, we’ll demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. In doing so, we’ll decipher practical knowledge of the domain of deep learning.  We’ll build and train neural networks that recognize handwriting and classify food in a scene. 

Objectives

Along the way, you’ll see MATLAB features that make it easy 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

When

  • Monday, June 11, 2018 10:00 AM - 12:00 PM:  MATLAB Demo
  • Monday, June 11, 2018 1:00 PM - 2:00 PM: Hand-on with MATLAB

For questions, please contact Doug Joubert at douglas.joubert@nih.gov

If you want to suggest a change, please let us know. Suggest a Class