Optimization research on Artificial Neural network Model

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Zhao:2011:ICCSNT,

• author = "Zhao Huanping and Lv Congying and Yang Xinfeng",
• title = "Optimization research on Artificial Neural network Model",
• booktitle = "International Conference on Computer Science and Network Technology (ICCSNT 2011)",
• year = "2011",
• month = "24-26 " # dec,
• volume = "3",
• pages = "1724--1727",
• address = "Harbin",
• abstract = "Optimisation Research on Artificial Neural Tree Network Model is divided into two parts: optimising topology structure and optimising parameters. For optimising topology structure, building-block-library based genetic programming algorithm, anarchical variable probability vector based probabilistic incremental program evolution algorithm and tree-encoded based particle swarm optimisation algorithm are proposed. The above algorithms can effectively reduce the number of invalid individuals generated in evolution process, improve the convergence speed and error precision of the NTNM. For optimising parameters, differential evolution algorithm is introduced. It has characteristics of less parameters to control, easier to implement and uneasy to fall into local minimum, etc. which make it very suitable for the optimisation of parameters.",
• keywords = "genetic algorithms, genetic programming, NTNM, anarchical variable probability vector, artificial neural network model, artificial neural tree network model, building-block-library based genetic programming algorithm, convergence speed, differential evolution algorithm, error precision, evolution process, invalid individuals, optimisation research, optimising parameters, optimising topology structure, parameter optimisation, probabilistic incremental program evolution algorithm, tree-encoded based particle swarm optimisation algorithm, convergence, neural nets, particle swarm optimisation, probability, topology, trees (mathematics), vectors",
• DOI = "doi:10.1109/ICCSNT.2011.6182301",
• notes = "Also known as \cite{6182301}",

}

Genetic Programming entries for Huanping Zhao Congying Lv Xinfeng Yang

Citations