ML Anthology

On a Magnitude Preserving Iterative MAXnet Algorithm

Bruce W. Suter, Matthew Kabrisky
NeCo 1992 pp. 224-233
doi:10.1162/NECO.1992.4.2.224 /neco/1992/suter1992neco-magnitude/

Abstract

A new iterative maximum picking neural net (MAXnet) is presented. This formulation determines the value and the location either for a unique maximum or for multiple maxima. This new net converges, for many commonly occurring distributions, in O(log M) iterations using only simple computing elements.

NeCo Semantic Scholar

Cite

Text

Suter and Kabrisky. "On a Magnitude Preserving Iterative MAXnet Algorithm." Neural Computation, 1992. doi:10.1162/NECO.1992.4.2.224

Markdown

[Suter and Kabrisky. "On a Magnitude Preserving Iterative MAXnet Algorithm." Neural Computation, 1992.](https://mlanthology.org/neco/1992/suter1992neco-magnitude/) doi:10.1162/NECO.1992.4.2.224

BibTeX

@article{suter1992neco-magnitude,
  title     = {{On a Magnitude Preserving Iterative MAXnet Algorithm}},
  author    = {Suter, Bruce W. and Kabrisky, Matthew},
  journal   = {Neural Computation},
  year      = {1992},
  pages     = {224-233},
  doi       = {10.1162/NECO.1992.4.2.224},
  volume    = {4},
  url       = {https://mlanthology.org/neco/1992/suter1992neco-magnitude/}
}