Deep Learning Demystified: Next-Generation Artificial Intelligence Applied to Video

Deep Learning Demystified: Next-Generation Artificial Intelligence Applied to Video

April 11, 2019, 9:45 AM - 10:45 AM

Sands 201

There’s a mystique surrounding the terms “Deep Learning” and “Artificial Intelligence”. The session aims to dispel the myths and present, in practical terms, what AI can and can’t do. 

The science of AI has long been part of daily life since the 1950s but only recently, AI has begun making its way into security applications and video surveillance. While AI holds the promise of fully automated video surveillance, and costs to implement these techniques have dropped significantly, there are also real limitations and even pitfalls. The session will provide an introduction to AI-related terminology, outline the technical foundations of Machine Vision and Machine Learning as applied to video, discuss how self-learning algorithms are forming the next generation of video analytics, and provide “Data dos and don’ts” for getting the best performance out of AI models.

Learning Objectives:

1. Differentiate clearly between the concepts of “Machine Learning” “Deep Learning” “Artificial Intelligence” and “Data Analysis”.
2. Recognize the capabilities and limitations of Artificial Intelligence and Deep Learning as applied to video.
3. Expand on the topics of building data sets, training models and maintaining quality.


  • AJ Frazer


    VP Business Development Cloud Services

    Agent Video Intelligence

    Mr. AJ Frazer has extensive product and business development experience with complex voice/video/data products and services. His career includes the...



  1. Track
    Video Surveillance

We use cookies to operate this website and to improve its usability. Full details of what cookies are, why we use them and how you can manage them can be found by reading our Privacy & Cookies page. Please note that by using this site you are consenting to the use of cookies.