On Mon, Feb 25, 2019 at 12:31 AM Linas Vepstas <linasveps...@gmail.com> wrote: > On Sun, Feb 24, 2019 at 6:34 PM Rob Freeman <chaotic.langu...@gmail.com> > wrote: > > Sergio Pissanetzky comes close to this, with his analysis in terms of > > permutations, also resulting in a network: > > "Structural Emergence in Partially Ordered Sets is the Key to Intelligence" > http://sergio.pissanetzky.com/Publications/AGI2011.pdf > > I'll look. Is it actually that good?
He lost me when he made the giant leap that this was the key to intelligence, like this is how the brain works. The paper mostly references his own work plus a few textbooks and irrelevant articles. Anyway he claims that minimizing the cost function of a partially ordered set solves all sorts of problems, like visual clustering, discovering Newtonian mechanics, deriving class hierarchies in procedural code (referenced in his other papers that I didn't read), and parallel CPU scheduling. His examples don't seem to apply the transitive property (A < B and B < C doesn't imply A < C), which would make it a directed acyclic graph instead. All of his examples are trees. The cost is defined as twice the total length of the edges when all the vertices are arranged in a straight line. (Twice for the "profound" reason that in a characteristic matrix representation, it's the distance from the diagonal and back, which he calls a "flux line"). The minimization can be solved (I think) iteratively by inducing a "block structure", which I think means merging leaf nodes into their siblings and parents. He doesn't give an algorithm, in keeping with the paper's lack of mathematical rigor or standard terminology. (He never mentions graphs, trees, vertices, edges, etc). -- -- Matt Mahoney, mattmahone...@gmail.com ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Ta6fce6a7b640886a-M53a991ee74e797cacf630fc2 Delivery options: https://agi.topicbox.com/groups/agi/subscription
