Neuro-evolution using recombinational algorithms and embryogenesis for robotic control

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

@PhdThesis{AnthonyMRoy:thesis,

• author = "Anthony M. Roy",
• title = "Neuro-evolution using recombinational algorithms and embryogenesis for robotic control",
• school = "Engineering and Applied Science, California Institute of Technology",
• year = "2009",
• address = "USA",
• month = "11 " # dec,
• keywords = "genetic algorithms, genetic programming, ANN, Neural Network, Robotics, Artificial Intelligence",
• URL = "http://thesis.library.caltech.edu/5944/",
• URL = "http://thesis.library.caltech.edu/5944/1/main.pdf",
• DOI = "doi:10.7907/YNED-VN66",
• size = "192 pages",
• abstract = "Control tasks involving dramatic nonlinearities, such as decision making, can be challenging for classical design methods. However, autonomous, stochastic design methods such as evolutionary computation have proved effective. In particular, genetic algorithms that create designs via the application of recombinational rules are robust and highly scalable. Neuro-Evolution Using Recombinational Algorithms and Embryogenesis (NEURAE) is a genetic algorithm that creates C++ programs that in turn create neural networks which can function as logic gates. The neural networks created are scalable and robust enough to feature redundancies that allow the network to function despite internal failures. An analysis of NEURAE evinces how biologically inspired phenomena apply to simulated evolution. This allows for an optimisation of NEURAE that enables it to create controllers for a simulated swarm of Khepera-inspired robots.",
• notes = "Antonsson, Erik K. (co-advisor) Shapiro, Andrew A. (co-advisor) Burdick, Joel Wakeman (advisor)",

}

Genetic Programming entries for Anthony M Roy

Citations