Repeat Until Bored: A Pattern Selection Strategy

Abstract

An alternative to the typical technique of selecting training examples independently from a fixed distribution is fonnulated and analyzed, in which the current example is presented repeatedly until the error for that item is reduced to some criterion value, ~; then, another item is ran(cid:173) domly selected. The convergence time can be dramatically increased or decreased by this heuristic, depending on the task, and is very sensitive to the value of ~.

Cite

Text

Munro. "Repeat Until Bored: A Pattern Selection Strategy." Neural Information Processing Systems, 1991.

Markdown

[Munro. "Repeat Until Bored: A Pattern Selection Strategy." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/munro1991neurips-repeat/)

BibTeX

@inproceedings{munro1991neurips-repeat,
  title     = {{Repeat Until Bored: A Pattern Selection Strategy}},
  author    = {Munro, Paul W.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {1001-1008},
  url       = {https://mlanthology.org/neurips/1991/munro1991neurips-repeat/}
}