English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Stochastic Gradient Descent Training of Ensembles of DT-CNN Classifiers for Digit Recognition

Merkwirth, C., Ogorzalek, M., & Wichard, J. D. (2003). Stochastic Gradient Descent Training of Ensembles of DT-CNN Classifiers for Digit Recognition. In Proceedings of the 16th European Conference on Circuit Theory and Design ECCTD'03 (pp. 337-341). Krakow, Poland: Faculty of Electrical Engineering, Automatics, Computer Science and Electronics, AGH University of Science and Technology.

Item is

Files

show Files
hide Files
:
457.pdf (Any fulltext), 284KB
 
File Permalink:
-
Name:
457.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Merkwirth, Christian1, Author           
Ogorzalek, Maciej, Author
Wichard, Jörg Daniel, Author
Ogorzalek, Maciej, Editor
Galias, Zbigniew, Editor
Garda, Bartłomiej, Editor
Kadeja, Bartłomiej, Editor
Affiliations:
1Computational Biology and Applied Algorithmics, MPI for Informatics, Max Planck Society, ou_40046              

Content

show
hide
Free keywords: -
 Abstract: We show how to train Discrete Time Cellular Neural Networks (DT-CNN) successfully by backpropagation to perform pattern recognition on a data set of handwritten digits. By using concepts and techniques from Machine Learning, we can outperform Support Vector Machines (SVM) on this problem.

Details

show
hide
Language(s): eng - English
 Dates: 2004-07-122003
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 201998
Other: Local-ID: C125673F004B2D7B-D22546C0E6C688C6C1256E19003E789C-Merkwirth2003ECCTD
 Degree: -

Event

show
hide
Title: ECCTD 2003
Place of Event: Krakow, Poland
Start-/End Date: 2003-09-01 - 2003-09-04

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the 16th European Conference on Circuit Theory and Design ECCTD'03
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Krakow, Poland : Faculty of Electrical Engineering, Automatics, Computer Science and Electronics, AGH University of Science and Technology
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 337 - 341 Identifier: ISBN: 83-88309-95-1