ML Anthology

A New On-Line Learning Model

Shahar Mendelson
NeCo 2001 pp. 935-957
doi:10.1162/089976601300014411 /neco/2001/mendelson2001neco-new/

Abstract

We introduce a new supervised learning model that is a nonhomogeneous Markov process and investigate its properties. We are interested in conditions that ensure that the process converges to a “correct state,” which means that the system agrees with the teacher on every “question.” We prove a sufficient condition for almost sure convergence to a correct state and give several applications to the convergence theorem. In particular, we prove several convergence results for well-known learning rules in neural networks.

NeCo Semantic Scholar

Cite

Text

Mendelson. "A New On-Line Learning Model." Neural Computation, 2001. doi:10.1162/089976601300014411

Markdown

[Mendelson. "A New On-Line Learning Model." Neural Computation, 2001.](https://mlanthology.org/neco/2001/mendelson2001neco-new/) doi:10.1162/089976601300014411

BibTeX

@article{mendelson2001neco-new,
  title     = {{A New On-Line Learning Model}},
  author    = {Mendelson, Shahar},
  journal   = {Neural Computation},
  year      = {2001},
  pages     = {935-957},
  doi       = {10.1162/089976601300014411},
  volume    = {13},
  url       = {https://mlanthology.org/neco/2001/mendelson2001neco-new/}
}