Some tasks such as Sudoku require serial steps of relational inference.
Recurrent relational network operates on a graph representation of objects. Message passing method is used to pass the relational information to neighbor nodes to solve the task. The loss is minimized at every step.
This module showed stablly better performance in bAbI task. RRN showed good performance in the newly defined Pretty-CLEVER task. This paper also showed this network solving Sudoku well.
It is clever to use message passing algorithm to solve relational tasks, but I think traing data is the issue(requires sequential answers for the task).
Subscribe via RSS