Examples of Learning Curves from a Modified VC-Formalism

Abstract

We examine the issue of evaluation of model specific parameters in a modified VC-formalism. Two examples are analyzed: the 2-dimensional homogeneous perceptron and the I-dimensional higher order neuron. Both models are solved theoretically, and their learning curves are com(cid:173) pared against true learning curves. It is shown that the formalism has the potential to generate a variety of learning curves, including ones displaying ''phase transitions."

Cite

Text

Kowalczyk et al. "Examples of Learning Curves from a Modified VC-Formalism." Neural Information Processing Systems, 1995.

Markdown

[Kowalczyk et al. "Examples of Learning Curves from a Modified VC-Formalism." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/kowalczyk1995neurips-examples/)

BibTeX

@inproceedings{kowalczyk1995neurips-examples,
  title     = {{Examples of Learning Curves from a Modified VC-Formalism}},
  author    = {Kowalczyk, Adam and Szymanski, Jacek and Bartlett, Peter L. and Williamson, Robert C.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {344-350},
  url       = {https://mlanthology.org/neurips/1995/kowalczyk1995neurips-examples/}
}