[SystemSafety] Breaking Down Problems with A.I. Safety

[Chuck_Petras at selinc.com]

You may find this interesting...

"Now comes the next OpenAI initiative: a breakdown of 'concrete problems 
in A.I. safety.' OpenAI researchers, in conjunction with colleagues from 
Google Brain, have issued a paper that delineates how machine-learning 
systems can potentially go haywire. ... 'Many of the problems are not new, 
but the paper explores them in the context of cutting-edge systems,' 
explains a brief intro on OpenAI?s Website. 'We hope they?ll inspire more 
people to work on A.I. safety research, whether at OpenAI or elsewhere.'" 
- 
http://insights.dice.com/2016/06/22/breaking-down-problems-with-ai-safety/

Concrete Problems in AI Safety
https://arxiv.org/pdf/1606.06565v1.pdf

And now there is this.

IBM WATSON AI XPRIZE [US$ 5MM] - INCENTIVIZING INNOVATIVE AI APPROACHES & 
COLLABORATION
http://ai.xprize.org/


Chuck Petras, PE**
Schweitzer Engineering Laboratories, Inc
Pullman, WA  99163  USA
http://www.selinc.com
Tel: +1.509.332.1890

SEL Synchrophasors - A New View of the Power System <
http://synchrophasor.selinc.com>

Making Electric Power Safer, More Reliable, and More Economical (R)

** Registered in Oregon.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.techfak.uni-bielefeld.de/mailman/private/systemsafety/attachments/20160624/92011e71/attachment.html>