Evaluation of Parameter Contribution to Neural Network Size and Fitness in ATHENA for Genetic Analysis

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

@InCollection{Li:2013:GPTP,

• author = "Ruowang Li and Emily R. Holzinger and Scott M. Dudek and Marylyn D. Ritchie",
• title = "Evaluation of Parameter Contribution to Neural Network Size and Fitness in ATHENA for Genetic Analysis",
• booktitle = "Genetic Programming Theory and Practice XI",
• year = "2013",
• series = "Genetic and Evolutionary Computation",
• editor = "Rick Riolo and Jason H. Moore and Mark Kotanchek",
• publisher = "Springer",
• chapter = "12",
• pages = "211--224",
• address = "Ann Arbor, USA",
• month = "9-11 " # may,
• keywords = "genetic algorithms, genetic programming, Grammatical evolution, Neural networks, Data mining, Human genetics, Systems biology, XOR model",
• isbn13 = "978-1-4939-0374-0",
• DOI = "doi:10.1007/978-1-4939-0375-7_12",
• abstract = "The vast amount of available genomics data provides us an unprecedented ability to survey the entire genome and search for the genetic determinants of complex diseases. Until now, Genome-wide association studies have been the predominant method to associate DNA variations to disease traits. GWAS have successfully uncovered many genetic variants associated with complex diseases when the effect loci are strongly associated with the trait. However, methods for studying interaction effects among multiple loci are still lacking. Established machine learning methods such as the grammatical evolution neural networks (GENN) can be adapted to help us uncover the missing interaction effects that are not captured by GWAS studies. We used an implementation of GENN distributed in the software package ATHENA (Analysis Tool for Heritable and Environmental Network Associations) to investigate the effects of multiple GENN parameters and data noise levels on model detection and network structure. We concluded that the models produced by GENN were greatly affected by algorithm parameters and data noise levels. We also produced complex, multi-layer networks that were not produced in the previous study. In summary, GENN can produce complex, multi-layered networks when the data require it for higher fitness and when the parameter settings allow for a wide search of the complex model space.",
• notes = "

  Part of \cite{Riolo:2013:GPTP} published after the workshop in 2013",

}

Genetic Programming entries for Ruowang Li Emily Rose Holzinger Scott M Dudek Marylyn D Ritchie

Citations