Representation and Extrapolation in Multi-Layer Perceptrons

Browne, Antony (2001) Representation and Extrapolation in Multi-Layer Perceptrons. [Preprint]

Full text available as:

[img] Postscript


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.

Item Type:Preprint
Keywords:Extrapolation, distributed representation, localist representation, identity task, circular convolution.
Subjects:Psychology > Cognitive Psychology
Computer Science > Artificial Intelligence
Computer Science > Neural Nets
ID Code:1904
Deposited By: Antony, Browne
Deposited On:19 Nov 2001
Last Modified:11 Mar 2011 08:54


Repository Staff Only: item control page