Cogprints

How to Make a Low-Dimensional Representation Suitable for Diverse Tasks

Intrator, Nathan and Edelman, Shimon (1996) How to Make a Low-Dimensional Representation Suitable for Diverse Tasks. [Preprint]

Full text available as:

[img] Postscript
1986Kb

Abstract

We consider training classifiers for multiple tasks as a method for improving generalization and obtaining a better low-dimensional representation. To that end, we introduce a hybrid training methodology for MLP networks; the utility of the hidden-unit representation is assessed by embedding it into a 2D space using multidimensional scaling. The proposed methodology is tested on a highly nonlinear image classification task.

Item Type:Preprint
Subjects:Psychology > Cognitive Psychology
ID Code:571
Deposited By: Edelman, Shimon
Deposited On:17 Nov 1997
Last Modified:11 Mar 2011 08:54

Metadata

Repository Staff Only: item control page