Course Description
Please join Rohde & Schwarz as we present a seminar in two parts:
Cognitive EW: Assuring In-Mission Learning for EW
This presentation will discuss the challenges for assuring the performance of a system that can learn from novel experiences in the field. EW systems operate at a timescale that means they cannot afford to learn post-mission, or with human supervision. EW systems must learn from a single observation, using self-supervised reinforcement feedback. The validation infrastructure must therefore support automated closed-loop, multi-resolution testing, and ways to test the effectiveness of actions. We must validate the learning process, rather than validating the learned model.
Cognitive EW: Data Requirements for AI
A common myth is that we need a lot of data to train an AI-ML system. This myth not only causes developers to fear data collection, but also causes developers to create solutions that are not fieldable. EW systems can leverage first-principle models (such as physics), feature engineering, and progression of the engagement to dramatically reduce the data collection requirements, and create systems that can learn on single observations of novel environments.
Agenda
10:30 AM — 11:00 AM
► Registration & seating
11:00 AM — 1:00 PM
► Cognitive EW: Assuring In-Mission Learning for EW
1:00 PM — 2:00 PM
► Lunch
2:00 PM — 4:00 PM
► Cognitive EW: Data Requirements for AI
Please arrive before the session to allow for registration & seating.
