ML Anthology

Representation and Extrapolation in Multilayer Perceptrons

Antony Browne
NeCo 2002 pp. 1739-1754
doi:10.1162/08997660260028692 /neco/2002/browne2002neco-representation/

Abstract

To give an adequate explanation of cognition and perform certain practical tasks, connectionist systems must be able to extrapolate. This work explores the relationship between input representation and extrapolation, using simulations of multilayer perceptrons trained to model the identity function. It has been discovered that representation has a marked effect on extrapolation.

NeCo Semantic Scholar

Cite

Text

Browne. "Representation and Extrapolation in Multilayer Perceptrons." Neural Computation, 2002. doi:10.1162/08997660260028692

Markdown

[Browne. "Representation and Extrapolation in Multilayer Perceptrons." Neural Computation, 2002.](https://mlanthology.org/neco/2002/browne2002neco-representation/) doi:10.1162/08997660260028692

BibTeX

@article{browne2002neco-representation,
  title     = {{Representation and Extrapolation in Multilayer Perceptrons}},
  author    = {Browne, Antony},
  journal   = {Neural Computation},
  year      = {2002},
  pages     = {1739-1754},
  doi       = {10.1162/08997660260028692},
  volume    = {14},
  url       = {https://mlanthology.org/neco/2002/browne2002neco-representation/}
}