Building Computer Vision Applications

We’re at a pivotal moment in time where Generative AI opens up numerous opportunities for innovation, akin to the revolutionary impact of electricity in its time. AI is not only reshaping tech but also extending its reach across every sector.

Join Andrew Ng in this livestream to learn how to quickly build your own custom computer vision models. Image data is pervasive, and in an hour, you’ll learn how to:

• Identify and scope vision applications. Is an application idea technically feasible? How much data would you need? What inputs and outputs should you pick for the vision model?
• Choose a vision project type/model. Can your application be built using Object Detection, Semantic Segmentation, Image Classification, or something else?
• Apply Data-Centric AI. Drive a rapid iterative development process via systematically identifying and fixing data problems.
• Deploy a Computer Vision model. Go from initial model development through live deployment.

These ideas will be illustrated with multiple practical use cases in manufacturing, healthcare, life sciences, satellite imagery, retail, and other sectors. This livestream will use the LandingLens platform to go through these concepts, and will also touch on advanced topics such as visual prompting.

Computer vision today feels like where large language models (LLMs) were 2 years ago. There’s a wealth of exciting computer vision yet to be built, and we hope this livestream will empower you to identify and build some of them!

To join us and access the livestream taking place on the LandingLens platform Monday, November 6th at 10:00 am PT, simply:

1. Create your free LandingLens account at app.landing.ai/signup
2. Verify your email to activate your account
3. Login to your account on November 6th at 10:00am PT and the livestream will automatically be playing on the LandingLens homepage

If you are unable to attend the live event, you can still register to receive information after the event.