TY - GEN
T1 - Implicit learning of common sense for reasoning
AU - Juba, Brendan
PY - 2013
Y1 - 2013
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/84896063714
M3 - Conference contribution
AN - SCOPUS:84896063714
SN - 9781577356332
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 939
EP - 946
BT - IJCAI 2013 - Proceedings of the 23rd International Joint Conference on Artificial Intelligence
T2 - 23rd International Joint Conference on Artificial Intelligence, IJCAI 2013
Y2 - 3 August 2013 through 9 August 2013
ER -