Agapitos, AlexandrosAlexandrosAgapitosO'Neill, MichaelMichaelO'NeillNicolau, MiguelMiguelNicolauFagan, DavidDavidFaganKattan, AhmedAhmedKattanCurran, Kathleen M.Kathleen M.Curran2017-01-162017-01-162015 IEEE2015-05-28http://hdl.handle.net/10197/82742015 IEEE Congress on Evolutionary Computation (CEC), Sendai, Japan, 25-28 May 2015A 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.en© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Object recognitionFeature extractionGenetic algorithmsHandwritten character recognitionConference Publication10.1109/CEC.2015.72571892016-11-15https://creativecommons.org/licenses/by-nc-nd/3.0/ie/