Re:Chomsky and the Two Cultures of Statistical Learning
by Alexander-Barth on Friday November 06, 2026 @12:39PM
(#50395576)
That is true, but to me it seems like ternary logic is like probabilities in disguise (false, true and unknown would be probability of 0, 1, and "between 0 and 1"). For most application, the unknown class is too broad, thus we need actual probabilities. But indeed, ternary logic is simpler than working with probabilities.
[ Parent
| on HN ]
There are no comments on this comment yet.