Deep Evolution of Feature Representations for Handwritten Digit Recognition
|Title:||Deep Evolution of Feature Representations for Handwritten Digit Recognition||Authors:||Agapitos, Alexandros; O'Neill, Michael; Nicolau, Miguel; Fagan, David; Kattan, Ahmed; Curran, Kathleen M.||Permanent link:||http://hdl.handle.net/10197/8274||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 recognition; Feature extraction; Genetic algorithms; Handwritten 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|
|Appears in Collections:||Business Research Collection|
CASL Research Collection
Show full item record
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.