Relational learning re-examined
Keyword(s):
We argue that existing learning algorithms are often poorly equipped to solve problems involving a certain type of important and widespread regularity that we call “type-2 regularity.” The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pursued including simple incremental learning, modular connectionism, and the developmental hypothesis of “representational redescription.”
Keyword(s):
2008 ◽
Vol 21
(02)
◽
pp. 183-203
◽
Keyword(s):
2020 ◽
Vol 34
(03)
◽
pp. 2569-2576
Keyword(s):
Keyword(s):
Keyword(s):