overlearning


Also found in: Dictionary, Wikipedia.

o·ver·learn·ing

(ō'vĕr-lern'ing),
In the psychology of memory, continuation of practice beyond the point at which one is able to perform according to the specified criterion; typically, retention is longer after overlearning compared with retention after practice only to the point of performance meeting the specified criterion.

o·ver·learn·ing

(ō'vĕr-lĕrn'ing)
In the psychology of memory, continuation of practice beyond the point at which one is able to perform according to the specified criterion.
References in periodicals archive ?
Relative effect of overlearning on reversal and nonreversal shifts with two and four sorting categories.
Overlearning and Distributed Practise on the Retention of Mathematics
Hence, Freedman suggests, "whenever explicit teaching does take place, there is risk of overlearning or misapplication" (226).
(82) While agreeing it would not be expedient to disregard the tactical considerations represented by minimalism, they nonetheless describe minimalism as "a gamble on an uncertain future--a bet that the Court will not tilt irretrievably conservative, that state-level constitutional bans on same-sex marriage can be overcome through political process, and that we are learning (but not overlearning) the right lessons from our complicated past." (83) Thus, they conclude, "[a] measure of modesty in addressing these questions--whether we should be minimalist in litigation and in the goals of adjudication and, if so, how--will remain critical as LGBT rights advocates move forward." (84)
Among them, unsupervised discriminant projection (UDP) [21], as a simplified version of LPP [35], is a very popular method with the aim of resolving the "overlearning locality" existing in LPP.
From Table 3, the structure NNFM(0) = NNFM(6, 3,2) is selected to avoid the phenomenon of overlearning. Adding more nodes in hidden layers does not improve the performance of NNFM(0).
(2) Use the training data to construct a neural network h : [R.sup.m] [right arrow] R, meanwhile evaluating the error of the neural network on the testing set to prevent overlearning and overfitting.