ML Anthology

Generalization and Approximation Capabilities of Multilayer Networks

Yoshikane Takahashi
NeCo 1993 pp. 132-139
doi:10.1162/NECO.1993.5.1.132 /neco/1993/takahashi1993neco-generalization/

Abstract

This paper develops a theory for constructing 3-layered networks. The theory allows one to specify a finite discrete set of training data and a network structure (minimum intermediate units, synaptic weights and biases) that generalizes and approximates any given continuous mapping between sets of contours on a plane within any given permissible error.

NeCo Semantic Scholar

Cite

Text

Takahashi. "Generalization and Approximation Capabilities of Multilayer Networks." Neural Computation, 1993. doi:10.1162/NECO.1993.5.1.132

Markdown

[Takahashi. "Generalization and Approximation Capabilities of Multilayer Networks." Neural Computation, 1993.](https://mlanthology.org/neco/1993/takahashi1993neco-generalization/) doi:10.1162/NECO.1993.5.1.132

BibTeX

@article{takahashi1993neco-generalization,
  title     = {{Generalization and Approximation Capabilities of Multilayer Networks}},
  author    = {Takahashi, Yoshikane},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {132-139},
  doi       = {10.1162/NECO.1993.5.1.132},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/takahashi1993neco-generalization/}
}