Repository logo
  • Log In
    New user? Click here to register.Have you forgotten your password?
University College Dublin
  • Colleges & Schools
  • Statistics
  • All of DSpace
  • Log In
    New user? Click here to register.Have you forgotten your password?
  1. Home
  2. College of Business
  3. School of Business
  4. Business Research Collection
  5. Deep Evolution of Feature Representations for Handwritten Digit Recognition
 
  • Details
Options

Deep Evolution of Feature Representations for Handwritten Digit Recognition

File(s)
FileDescriptionSizeFormat
Download agapitos2015a.pdf465.95 KB
Author(s)
Agapitos, Alexandros 
O'Neill, Michael 
Nicolau, Miguel 
Fagan, David 
Kattan, Ahmed 
Curran, Kathleen M. 
Uri
http://hdl.handle.net/10197/8274
Date Issued
28 May 2015
Date Available
16T18:01:25Z January 2017
Abstract
A training protocol for learning deep neural networks, called greedy layer-wise training, is applied to the evolution of a hierarchical, feed-forward Genetic Programming based system for feature construction and object recognition. Results on a popular handwritten digit recognition benchmark clearly demonstrate that two layers of feature transformations improves generalisation compared to a single layer. In addition, we show that the proposed system outperforms several standard Genetic Programming systems, which are based on hand-designed features, and use different program representations and fitness functions.
Type of Material
Conference Publication
Publisher
IEEE
Copyright (Published Version)
2015 IEEE
Keywords
  • Object recognition

  • Feature extraction

  • Genetic algorithms

  • Handwritten character...

DOI
10.1109/CEC.2015.7257189
Language
English
Status of Item
Peer reviewed
Description
2015 IEEE Congress on Evolutionary Computation (CEC), Sendai, Japan, 25-28 May 2015
This item is made available under a Creative Commons License
https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Owning collection
Business Research Collection
Scopus© citations
10
Acquisition Date
Feb 1, 2023
View Details
Views
1638
Acquisition Date
Feb 1, 2023
View Details
Downloads
180
Last Week
6
Last Month
59
Acquisition Date
Feb 1, 2023
View Details
google-scholar
University College Dublin Research Repository UCD
The Library, University College Dublin, Belfield, Dublin 4
Phone: +353 (0)1 716 7583
Fax: +353 (0)1 283 7667
Email: mailto:research.repository@ucd.ie
Guide: http://libguides.ucd.ie/rru

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science

  • Cookie settings
  • Privacy policy
  • End User Agreement