title: How to Make a Low-Dimensional Representation Suitable for Diverse Tasks
creator: Intrator, Nathan
creator: Edelman, Shimon
subject: Cognitive Psychology
description: 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.
date: 1996
type: Preprint
type: NonPeerReviewed
format: application/postscript
identifier: http://cogprints.org/571/2/199711005.ps
identifier:   Intrator, Nathan and Edelman, Shimon  (1996) How to Make a Low-Dimensional Representation Suitable for Diverse Tasks.  [Preprint]     
relation: http://cogprints.org/571/