Explainable AI: Beware What You Wish For

Address: Daedalean AG
Albisriederstrasse 199
8047 Zürich
Switzerland
Phone: Connect: Website: View website Contact: Contact supplier View: View supplier

Explainable AI: Beware What You Wish For

2nd September 2022

Can ‘Explainable AI’ provide a way to apply DO-178C for the safety assurance of neural networks in aviation applications? We think not, but there are a few subtle misconceptions to be unwrapped.

However, there does exist a different approach for ensuring the reliable performance of machine-learned (‘AI’) components for a new generation of flight control instruments: demonstrating Machine Learning Generalization and quantifying so-called “Domain Gaps”.

This 8-minute video provides a synopsis of the concepts for anyone who has a basic understanding of high school-level math.

00:19 How DO-178 works for the classical software systems in aviation
01:00 What is that ‘AI’ you speak of
03:44 Certainty and uncertainty
04:56 Traceability: Beware of what you wish for
06:16 How to design a system with a component working with uncertainty
06:56 Will it work ‘in vivo’ as well as it worked ‘in vitro’?

daedalean.ai

Other Daedalean Videos

Latest Daedalean News

How Will a Modern City Actually Look With Urban Air Mobility?

How Will a Modern City Actually Look With Urban Air Mobility?

Daedalean has been awarded a grant by Innosuisse to develop its BRAVEN (Bimodal Radar for Aviation Environments) Solution.

How Visual Positioning Fills In When GPS Goes Down

How Visual Positioning Fills In When GPS Goes Down

Daedalean believes one of the three key skills of a human pilot is to fly according to visual flight rules (VFR) and in visual conditions.

Ensuring Safety and Certification of our Products

Ensuring Safety and Certification of our Products

At Daedalean, the team has always focused on developing products for aviation with an eye toward future certification.

The Importance of Enhancing General Aviation Safety: NTSB Data

The Importance of Enhancing General Aviation Safety: NTSB Data

Daedalean recently looked into accidents related to navigation, flight planning, geographic disorientation & navigation error.

Daedalean Tensor Accelerator

Daedalean Tensor Accelerator

Daedalean’s Visual Awareness System (VXS) relies on the input from several (one to four) cameras installed on an aircraft.

High Performance, Low SWaP, and Certifiable for Aviation

High Performance, Low SWaP, and Certifiable for Aviation

Daedalean leverages the power of artificial intelligence to provide superhuman situational awareness systems to aerospace.

Daedalean’s Aircraft Photoshoot

Daedalean’s Aircraft Photoshoot

Daedalean’s data-collection aircraft photoshoot in the Swiss Alps illustrates the beauty of nature and technology.

Daedalean Launches US Office, New President Appointed

Daedalean Launches US Office, New President Appointed

Daedalean hires Dr. Yemaya Bordain to lead its new office in Phoenix, AZ, as the company officially opens for business in the United States.

Neural Network-Based Runway Landing Guidance for Aviation

Neural Network-Based Runway Landing Guidance for Aviation

Daedalean has concluded a joint research project with the FAA on Neural Network-Based Runway Landing Guidance for General Aviation.

Avidyne and Daedalean Develop AI-Based Avionics Vision Systems

Avidyne and Daedalean Develop AI-Based Avionics Vision Systems

Avidyne Corporation and Daedalean AG are developing, manufacturing and certifying an AI-based avionics vision system together.

Contact Daedalean

Use the form opposite to get in touch with Daedalean directly to discuss any requirements you might have.









    We'd love to send you the latest news and information from the world of Future Transport-News. Please tick the box if you agree to receive them.

    For your peace of mind here is a link to our Privacy Policy.

    By submitting this form, you consent to allow Future Transport-News to store and process this information.

    Subscribe
    Follow Future Transport-News on LinkedIn
    Follow Future Transport-News on Twitter