Vague manifesto: neural networks are good at denotation (can represent an arbitrary function into some space of labels) but more generic edge-labelled graph representations can better represent networks of connotation (analogy, shoddy transitivity, etc.).
-
-
-
How about: there are well established training algorithms for neural networks...
- 2 more replies
New conversation -
-
-
Genetic programming?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.