Generalization is the ability of a fitted prediction rule to perform well on new observations under a specified target probability distribution. It is assessed through prediction error rather than training error. The target distribution and use of data are part of the question: dataset shift can change performance, and data leakage can make an apparent assessment misleading.
Generalizing known components or operations to combinations not encountered during training. A held-out combination split tests a different ability from random train–test splitting when both sets contain nearly identical constructions. A failure of a particular neural training setup does not prove a limitation of every network architecture.[ref]
Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks by Brenden M. Lake and others. Abstract and experiments; PMLR 80, pp. 2873–2882, systematic versus ordinary SCAN generalization
Articles by others on the same topic
There are currently no matching articles.