---
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.'
altloc: []
chapter: ~
commentary: ~
commref: ~
confdates: ~
conference: ~
confloc: ~
contact_email: ~
creators_id: []
creators_name:
  - family: Intrator
    given: Nathan
    honourific: ''
    lineage: ''
  - family: Edelman
    given: Shimon
    honourific: ''
    lineage: ''
date: 1996
date_type: published
datestamp: 1997-11-17
department: ~
dir: disk0/00/00/05/71
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 571
fileinfo: /style/images/fileicons/application_postscript.png;/571/2/199711005.ps
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: ~
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: ~
lastmod: 2011-03-11 08:54:05
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: ~
pubdom: FALSE
publication: ~
publisher: ~
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 10
series: ~
source: ~
status_changed: 2007-09-12 16:31:17
subjects:
  - cog-psy
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: How to Make a Low-Dimensional Representation Suitable for Diverse Tasks
type: preprint
userid: 43
volume: ~
<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>