- Source: Grokking (machine learning)
In machine learning, grokking, or delayed generalization, is a transition to generalization that occurs many training iterations after the interpolation threshold, after many iterations of seemingly little progress, as opposed to the usual process where generalization occurs slowly and progressively once the interpolation threshold has been reached.
The term derives from the word grok coined by Robert Heinlein in his novel Stranger in a Strange Land.
Grokking can be understood as a phase transition during the training process. While grokking has been thought of as largely a phenomenon of relatively shallow models, grokking has been observed in deep neural networks and non-neural models and is the subject of active research.
References
See also
Deep double descent