Deep Learning Series

In this 4-part Deep Learning Webinar Series you will learn how easy it can be to apply Deep Learning in your engineering and science projects using MATLAB and Simulink. With just a few lines of MATLAB code you can apply deep learning techniques to your work, from standard architectures for image and signal processing to advanced neural networks for a wide range of tasks. Also learn how automation can help you label your data more efficiently, and how optimization techniques for hyperparameters can be used to maximize the performance of your networks.

Each session features a guest speaker who will share their experiences with applying MATLAB and deep learning techniques to their projects in various industries.

The series focuses on the following topics:

• Demonstrate a workflow for how you can research, develop, and deploy your deep learning application
• Use and extend the Signal, Image and Video Labelers to automate your data labeling workflow
• Graphically create, edit, and train models
• Efficiently explore and optimize model hyperparameters with interactive apps and optimization-based approaches
• Customize and train advanced neural networks
• Generate realistic synthetic image data with GANs
• Implement generalized research models in MATLAB

About the Presenters

Guest Speakers

Session 1: David Kirschner, Research Geologist, Royal Dutch Shell, USA

Session 2: Raphaël Thierry, Novartis, Switzerland

Session 3: Arnie Berlin, Senior Application Engineer, MathWorks, USA

Session 4: Takato Yasuno, Senior Researcher, Yachiyo Engineering Company, Japan

MathWorks Speakers

Toon Weyens, Application Engineer, Netherlands

Paola Jaramillo, Application Engineer, Netherlands

Christoph Kammer, Application Engineer, Switzerland