No
Yes
View More
View Less
Working...
Close
OK
Cancel
Confirm
System Message
Delete
Schedule
An unknown error has occurred and your request could not be completed. Please contact support.
Scheduled
Wait Listed
Personal Calendar
Speaking
Conference Event
Meeting
Interest
Schedule TBD
Conflict Found
This session is already scheduled at another time. Would you like to...
Loading...
Please enter a maximum of {0} characters.
Please enter a maximum of {0} words.
must be 50 characters or less.
must be 40 characters or less.
Session Summary
We were unable to load the map image.
This has not yet been assigned to a map.
Search Catalog
Reply
Replies ()
Search
New Post
Microblog
Microblog Thread
Post Reply
Post
Your session timed out.
This web page is not optimized for viewing on a mobile device. Visit this site in a desktop browser to access the full set of features.
2017 GTC San Jose

S7832 - Illuminating AI: Understanding the AI's Goals, Reasoning and Compromises

Session Speakers
Session Description

Why does existing AI need to be explainable? Applying AI where someone may get hurt requires: safety regulation, explanation & understanding. But the internal decisions of AI are not explainable, earning a well-deserved designation of "black-box". Thus until AI becomes more transparent, applications will remain limited in fields where safety and understanding are paramount such as medicine, self-driving cars and banking. Illuminated AI helps debug your models by revealing goals of the network and insights from test cases. With this knowledge you, your customers and those who certify AI algorithms can be more confident of your AI. We enter a new era of introspective AI that is more trusted and safer, allowing broader applications in medicine, self-driving cars and banking.


Additional Session Information
Advanced
Talk
Deep Learning and AI Other
Financial Services General Healthcare & Life Sciences
50 minutes
Session Schedule