Implicit Learning of Common Sense for Reasoning

We consider the problem of how enormous databases of “common sense” knowledge can be both learned and utilized in reasoning in a computationally efficient manner. We propose that this is possible if the learning only occurs implicitly, i.e., without generating an explicit representation. We show that it is feasible to invoke such implicitly learned knowledge in essentially all natural tractable reasoning problems. This implicit learning also turns out to be provably robust to occasional counterexamples, as appropriate for such common sense knowledge.