Eugine_Nier comments on Understanding and justifying Solomonoff induction - Less Wrong

1 Post author: gedymin 15 January 2014 01:16AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (75)

You are viewing a single comment's thread. Show more comments above.

Comment author: Eugine_Nier 15 January 2014 05:29:55AM 0 points [-]

The only programs allowed in the Solomonoff distribution are ones that don't have any extended versions that produce the same output observed so far. So it's not that the longer programs are given lower probability - it's that they are given undefined probability, and are entirely "represented" by the most truncated version.

That depends on how one defines "Solomonoff induction".