Deep Learning for Computer Vision

Overview

While deep learning can achieve state-of-the-art accuracy for object recognition and object detection, it can be difficult to train, evaluate and compare deep learning models. Deep learning also requires a significant amount of data and computational resources.

In this webinar, we will explore how MATLAB^® addresses the most common deep learning challenges and gain insight into the procedure for training accurate deep learning models. We will cover new capabilities for deep learning and computer vision for object recognition and object detection.

Highlights

We will use real-world examples to demonstrate:

• Accessing and managing large sets of images
• Using visualization to gain insight into the training process
• Leveraging pretrained networks to perform new recognition tasks using transfer learning
• Speeding up the training process using GPUs and Parallel Computing Toolbox™

About the Presenter

Johanna Pingel joined the MathWorks team in 2013, specializing in Image Processing and Computer Vision applications with MATLAB. She has a M.S. degree from Rensselaer Polytechnic Institute and a B.A. degree from Carnegie Mellon University. She has been working in the Computer Vision application space for over 5 years, with a focus on object detection and tracking.