On Wed, Feb 19, 2020, 3:17 PM WriterOfMinds <[email protected]> wrote:
> No, to my knowledge the Winograd challenge has not been solved (at least, > not to the point of a program getting correct answers on all the sentences > in a test set). The only other hobbyist/independent researcher that I've > seen openly working on it is Don Patrick, who describes his approach and > results here if you feel like comparing: > > https://artistdetective.wordpress.com/2016/06/15/how-to-teach-a-computer-common-sense/ > Interesting that it is basically the same approach as Cyc in 1986. You program a bunch of rules defining common sense. Cyc succombed to the power law or Zipf distribution of knowledge. A few dozen rules cover half the cases. You need millions of rules to cover the rest. Cyc was a failure. But it is interesting that in 34 years we haven't found something better. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T887757e45bfd1342-M5e211378a29dbf7f90104e95 Delivery options: https://agi.topicbox.com/groups/agi/subscription
