Cognitive EW: Assuring In-Mission Learning for EW
To view complete details for this event, click here to view the announcement
Cognitive EW: Assuring In-Mission Learning for EW
Machine Learning (ML) can be relatively easy, if you have a server farm and humans in the loop. How do you make it happen when you have an isolated machine in arduous conditions?
This presentation will discuss the challenges for assuring the performance of a system that can learn from novel experiences in the field. Electronic Warfare (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.
Date and Time
- Date: 08 Nov 2024
- Time: 05:45 PM to 07:00 PM
- All times are (UTC-06:00) Central Time (US & Canada)
Add Event to Calendar
Location
- 1500 Engineering Drive
- Madison, Wisconsin
- United States 53706
- Building: Engineering Research Building
- Room Number: 106
Hosts
Registration
- Starts 26 October 2024 12:00 AM
- Ends 07 November 2024 05:00 PM
- All times are (UTC-06:00) Central Time (US & Canada)
- No Admission Charge
Speakers
Karen Haigh
Cognitive EW: Assuring In-Mission Learning for EW
Agenda
5:45 - Networking and pizza
6:00 - Administrative and introduction of speaker
6:05 - Presentation
6:50 - Question/answer period
Parking should be available in Ramp 17 at the west end of Engineering Drive.
There will be time for networking over pizza before the talk. Please register, so that we know how much pizza to get.
