Deep Learning on Title and Content Features to Tackle Clickbait

Re:Deep Learning on Title and Content Features to Tackle Cli... by astrodust on Monday March 13, 2017 @04:23PM (#13861990)

Just as "dogness" is a factor, so is "clickbaityness". You're right, this is all about thresholds.

[ Parent | on HN ]

Re:Deep Learning on Title and Content Features to Tackle Cli... by kristianc on Monday March 13, 2017 @07:01PM (#13863360)

I often wonder what Wittgenstein would have made of today's models of machine learning / deep learning https://en.m.wikipedia.org/wiki/Family_resemblance

[ Parent | on HN ]

Re:Deep Learning on Title and Content Features to Tackle Cli... by BooglyWoo on Tuesday March 14, 2017 @12:34PM (#13868984)

Me too. My reading of the Blue and Brown books led me to believe Wittgenstein's conception of meaning is inextricably tied up with the notion of "learning" and exposure to language and its use. Rather than meaning being contingent on 'hard' logico-mathematical derivations of formal semantics.

This contrast seems somewhat reminiscent of the complementary approaches of hard-coded rule based AI vs machine learning.

[ Parent | on HN ]