Presentation: Is It a Wolf or a Husky? Can You Trust Your AI Vision Model?
Presented by: Ted Way, Microsoft
Artificial intelligence is ubiquitous in computer vision applications — from self-driving cars to retail, healthcare, manufacturing, and beyond. How do you know your computer vision AI model is working as advertised?
In his presentation, Ted Way, Ph.D., a program manager lead for the Microsoft Insights Apps AI team, will cover various ways that AI models can be fooled, such as by adding stickers to a stop sign. The session will also focus on using techniques to probe how a vision AI model makes a decision. Finally, Way will show how the LIME (local interpretable model-agnostic explanations) technique explains what an AI model is doing when it's looking at pictures of wolves and huskies, for example.
The inaugural Vision Spectra Conference runs July 20 - 22. Registration is free for the event, which is offered exclusively online. For more information and registration, please visit www.photonics.com/vsc2021. Continued coverage of this inaugural event will also be available on vision-spectra.com and Photonics.com leading up to the conference.
|
|
|
|