How can robots learn ethical behavior if there is no “user manual” for being human? Researchers at Georgia Institute of Technology believe the answer lies in “Quixote“—a technique that teaches “value alignment” to robots by training them to read stories, learn acceptable sequences of events, and understand successful ways to behave in human societies.
Read more:
http://snapzu.com/gladsdotter/maybe-robots-wont-kill-us-if-they-read-good-books
No comments:
Post a Comment