gmaxwell comments on How An Algorithm Feels From Inside - Less Wrong

87 Post author: Eliezer_Yudkowsky 11 February 2008 02:35AM

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

Comments (77)

Sort By: Old

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

Comment author: gmaxwell 08 September 2010 04:55:52AM *  1 point [-]

Network 1 would work just fine (ignoring how you'd go about training such a thing). Each of the N^2 edges has a weight expressing the relationship of the vertices it connects. E.g. if nodes A and B are strongly anti-correlated the weight between them might be -1. You then fix the nodes you know and then either solve the system analytically or through numerical iteration until it settles down (hopefully!) and then you have expectations for all the unknown.

Typical networks for this sort of thing don't have cycles so stability isn't a question, but that doesn't mean that networks with cycles can't work and reach stable solutions. Some error correcting codes have graph representations that aren't much better than this. :)