Best-First Model Merging for Dynamic Learning and Recognition

Abstract

"Best-first model merging" is a general technique for dynamically choosing the structure of a neural or related architecture while avoid(cid:173) ing overfitting. It is applicable to both leaming and recognition tasks and often generalizes significantly better than fixed structures. We dem(cid:173) onstrate the approach applied to the tasks of choosing radial basis func(cid:173) tions for function learning, choosing local affine models for curve and constraint surface modelling, and choosing the structure of a balltree or bumptree to maximize efficiency of access.

Cite

Text

Omohundro. "Best-First Model Merging for Dynamic Learning and Recognition." Neural Information Processing Systems, 1991.

Markdown

[Omohundro. "Best-First Model Merging for Dynamic Learning and Recognition." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/omohundro1991neurips-bestfirst/)

BibTeX

@inproceedings{omohundro1991neurips-bestfirst,
  title     = {{Best-First Model Merging for Dynamic Learning and Recognition}},
  author    = {Omohundro, Stephen M.},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {958-965},
  url       = {https://mlanthology.org/neurips/1991/omohundro1991neurips-bestfirst/}
}