Machine learning at scale: Behind the scenes of Photoshop & Co

Data science and machine learning are present in all of Adobe’s offerings, from separating background from foreground in Photoshop, to identifying table structure in Acrobat, to anomaly detection on the Experience Cloud.

This talk will provide a high-level overview of the data science ecosystem throughout Adobe, covering a wide range of solutions and implementations, as well as some of the key tools and architectural decisions that enable performance of these algorithms at scale and over different types of software.

We’ll cover data science solutions that:

• Are delivered through the software-as-a-service model
• Perform computation on device, including mobile devices
• Provide self-service suite of tools for custom model building and deployment

Objective of the talk

If you still wonder about the practical use of ML/AI, this talk gives you insight into how multiple well-known projects incorporate a variety of approaches and the architectural decisions that made them successful