ML Anthology

Convergence Properties of Learning in ART1

Michael Georgiopoulos, Gregory L. Heileman, Juxin Huang
NeCo 1990 pp. 502-509
doi:10.1162/NECO.1990.2.4.502 /neco/1990/georgiopoulos1990neco-convergence/

Abstract

We consider the ART1 neural network architecture. It is shown that in the fast learning case, an ART1 network that is repeatedly presented with an arbitrary list of binary input patterns, self-stabilizes the recognition code of every size-l pattern in at most l list presentations.

NeCo Semantic Scholar

Cite

Text

Georgiopoulos et al. "Convergence Properties of Learning in ART1." Neural Computation, 1990. doi:10.1162/NECO.1990.2.4.502

Markdown

[Georgiopoulos et al. "Convergence Properties of Learning in ART1." Neural Computation, 1990.](https://mlanthology.org/neco/1990/georgiopoulos1990neco-convergence/) doi:10.1162/NECO.1990.2.4.502

BibTeX

@article{georgiopoulos1990neco-convergence,
  title     = {{Convergence Properties of Learning in ART1}},
  author    = {Georgiopoulos, Michael and Heileman, Gregory L. and Huang, Juxin},
  journal   = {Neural Computation},
  year      = {1990},
  pages     = {502-509},
  doi       = {10.1162/NECO.1990.2.4.502},
  volume    = {2},
  url       = {https://mlanthology.org/neco/1990/georgiopoulos1990neco-convergence/}
}