Instructors: Gilles Roux, Google
Level: Introductory

Benefits:
This course enables the attendee to:

• Gain foundational knowledge of ML/DL concepts.
• Develop an intuitive understanding by comparing ML/DL to traditional imaging algorithms.
• Enhance collaboration with ML specialists.
• Establish a basis for acquiring hands-on skills.

Course Description:
This class addresses the gap between traditional image processing techniques and modern machine learning (ML) approaches for camera and ISP engineers. It covers fundamental ML concepts, an introduction to deep learning with a focus on convolutional neural networks (CNNs) and their applicability to image processing. The emphasis is on building an intuitive understanding and highlighting the similarities and differences with traditional techniques.

Intended Audience: Imaging engineers who want to learn about machine and deep learning and how they can be applied to image processing.

Gilles Roux is an accomplished software engineer with more than 23 years of industry experience, including a 14-year tenure at Google where he has contributed to a wide range of products, including Google Analytics, Google Pay, and Google Photos. He is passionate about product development, user experience, machine learning, and computational photography. Currently leading an applied ML team within the Google Photos team, Roux focuses on building on-device ML models for image editing. His prior experience on the Sensor Intelligence team involved neural image processing and low-power sensing applications. Roux's experience in machine learning and its applications in imaging makes his insights particularly valuable for imaging engineers exploring the integration of ML into their work.