Genetic Programming with Gradient Descent Search for Multiclass Object Classification

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{zhang:2004:eurogp,

• author = "Mengjie Zhang and Will Smart",
• title = "Genetic Programming with Gradient Descent Search for Multiclass Object Classification",
• booktitle = "Genetic Programming 7th European Conference, EuroGP 2004, Proceedings",
• year = "2004",
• editor = "Maarten Keijzer and Una-May O'Reilly and Simon M. Lucas and Ernesto Costa and Terence Soule",
• volume = "3003",
• series = "LNCS",
• pages = "399--408",
• address = "Coimbra, Portugal",
• publisher_address = "Berlin",
• month = "5-7 " # apr,
• organisation = "EvoNet",
• publisher = "Springer-Verlag",
• keywords = "genetic algorithms, genetic programming: Poster",
• ISBN = "3-540-21346-5",
• DOI = "doi:10.1007/978-3-540-24650-3_38",
• abstract = "Use of gradient descent search in genetic programming (GP) for object classification problems. Gradient descent search is introduced to the GP mechanism and is embedded into the genetic beam search, which allows the evolutionary learning process to globally follow the beam search and locally follow the gradient descent search. Two different methods, an online gradient descent scheme and an off line gradient descent scheme, are developed and compared with the basic GP method on three image data sets with object classification problems of increasing difficulty. The results suggest that both the online and the offline gradient descent GP methods outperform the basic GP method in terms of both classification accuracy and training efficiency and that the online scheme achieved better performance than the off-line scheme.",
• notes = "Part of \cite{keijzer:2004:GP} EuroGP'2004 held in conjunction with EvoCOP2004 and EvoWorkshops2004",

}

Genetic Programming entries for Mengjie Zhang Will Smart

Citations