title: Representation and Extrapolation in Multi-Layer Perceptrons
creator: Browne, Antony
subject: Cognitive Psychology
subject: Artificial Intelligence
subject: Neural Nets
description: To give an adequate explanation of cognition and perform certain practical tasks connectionist systems must be able to extrapolate. This work has explored the relationship between input representation and extrapolation, using simulations of multi-layer perceptrons trained to model the identity function. It has been discovered that representation has a marked effect on extrapolation. 
date: 2001-10
type: Preprint
type: PeerReviewed
format: application/postscript
identifier: http://cogprints.org/1904/1/NcompExtrap.ps.zip
identifier:   Browne, Antony  (2001) Representation and Extrapolation in Multi-Layer Perceptrons.  [Preprint]     
relation: http://cogprints.org/1904/