Keynote: Trusted AI: Bringing Trust Back into AI through Open Source
Talkat Open Source Summit Europe + Embedded Linux Conference Europe 2019 · on Tuesday, 2019-10-29· at 10:15· Amphitheatre·
summary
AI failures can be tiny and catastrophic — a little adversarial noise can flip a panda to a monkey and break check scanners or loan decisions — so IBM releases practical open source tools to detect and repair issues. The GitHub Adversarial Robustness Toolbox inspects models and data, AI Fairness 360 offers roughly 70 functions to assess models in ten ways, and OpenScale dashboard tracks outcomes across the whole lifecycle. Join the Linux Foundation AI Committee or contribute on GitHub.
AI-written summary · about
chapters (13)
- 0:00Trust in AI
- 0:24Brad Topol
- 0:50Kevin Kelly
- 1:17Lighthearted
- 2:09adversarial attacks
- 2:50your life
- 3:10complex decisions
- 3:39data tampering
- 4:11open source
- 4:30adversarial robustness toolbox
- 5:32openscale dashboard
- 5:45Linux Foundation AI Committee
- 6:11IBM CodeA
related talks
32mHow to Build Trustworthy AI with Open Source
39mSponsored Session: The Search for Transparency and Accountability in the Age of AI: RAI & XAI as Essential Tools
22mThe Imperative for Open Source AI - The Path Forward to Take Down the AI Oligarchs
13mKeynote : The Open Source AI Alliance
33mBuilding Ethical AI: The Power of Open Source and Education
36mKeynote: Ethics in AI: Building Fair and Just Intelligence Systems
46mCan you trust your AI?- 39mThe Search for Transparency and Accountability in the Age of...