Skip to content
Assuring AI episode artwork

Dec 18, 2017 53 min

Assuring AI

from International Conference on Functional Programming 2017

John Launchbury, Chief Scientist of Galois Inc, gives the second keynote of the ICFP conference. Somewhat ironically, just as traditional systems software finally comes within reach of detailed mathematical verification, the demand for verification technology is rapidly expanding into domains that pose very different kinds of challenges. How could a face recognition technology be verified, for example, when it is not clear even how to state a correctness property? Or how should we attempt to verify an autonomous system like a self-driving car? This talk will attempt to lay out the problem space, and offer some ideas for how the verification community might start tackling the problem of assuring AI.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Assuring AI

0:00 53:21

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of International Conference on Functional Programming 2017?

This episode is 53 minutes long.

When was this International Conference on Functional Programming 2017 episode published?

This episode was published on December 18, 2017.

Can I download this International Conference on Functional Programming 2017 episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.