Deep Evolution of Feature Representations for Handwritten Digit Recognition

Files in This Item:
File Description SizeFormat 
agapitos2015a.pdf465.95 kBAdobe PDFDownload
Title: Deep Evolution of Feature Representations for Handwritten Digit Recognition
Authors: Agapitos, AlexandrosO'Neill, MichaelNicolau, MiguelFagan, DavidKattan, AhmedCurran, Kathleen M.
Permanent link:
Date: 28-May-2015
Online since: 2017-01-16T18:01:25Z
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 recognitionFeature extractionGenetic algorithmsHandwritten character recognition
DOI: 10.1109/CEC.2015.7257189
Language: en
Status of Item: Peer reviewed
Conference Details: 2015 IEEE Congress on Evolutionary Computation (CEC), Sendai, Japan, 25-28 May 2015
This item is made available under a Creative Commons License:
Appears in Collections:Business Research Collection
CASL Research Collection

Show full item record

Citations 50

Last Week
Last month
checked on Sep 11, 2020

Page view(s) 50

Last Week
Last month
checked on Apr 17, 2021


checked on Apr 17, 2021

Google ScholarTM



If you are a publisher or author and have copyright concerns for any item, please email and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.