• Login
    View Item 
    •   Carroll Scholars Home
    • Mathematics, Engineering and Computer Science
    • Mathematics, Engineering and Computer Science Undergraduate Theses
    • View Item
    •   Carroll Scholars Home
    • Mathematics, Engineering and Computer Science
    • Mathematics, Engineering and Computer Science Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Implementing a Greedy Crossover Operator for Cooperative Coevolution of Neural Networks

    Thumbnail
    View/Open
    2009_DunhamB_THS_000570.pdf (1.949Mb)
    Author
    Dunham, Ben
    Advisor
    Kelly Cline; Steve Harper; Jeff Morris
    Date of Issue
    2009-04-01
    Metadata
    Show full item record
    URI
    https://scholars.carroll.edu/handle/20.500.12647/3424
    Title
    Implementing a Greedy Crossover Operator for Cooperative Coevolution of Neural Networks
    Type
    thesis
    Abstract
    Work was done towards a new crossover operator for the “Hierarchical-Enforced SubPopulations” (H-ESP) neuroevolution algorithm. The new operator takes advantage of the per-neuron fitness evaluations available in H-ESP Layer 1 to systematically replace the least-fit neurons in champion (Layer 2) networks. To implement this operator, two other changes were required: First, rather than evaluate each neuron only once per generation, each is used in two different networks and tested with a half-fidelity simulation. This gives a finer-grain indication of each neuron’s individual contribution to network fitness. Second, to maintain current evaluations of any Layer 2 neurons not dual-listed in Layer 1, all such nodes are reinjected back into LI. By itself, the fine-grain neuron fitness measure provides a significant boost in performance: the algorithm optimizes faster, and completes successfully more often. Using LI reinjection provides a smaller but still noticeable improvement beyond this. Surprisingly, the node replacement operator itself does not provide a noticeable net benefit on top of these two (supposedly corollary) changes: the penalty incurred by evaluating additional networks appears to cancel any benefit granted by intelligent crossover. Although the improvements did not come from the direction expected, this work has successfully extended the H-ESP algorithm. Moreover, the extensions are not limited to neuroevolution: Any cooperative coevolution paradigm could benefit from the lessons learned here.
    Degree Awarded
    Bachelor's
    Semester
    Spring
    Department
    Mathematics, Engineering & Computer Science
    Collections
    • Mathematics, Engineering and Computer Science Undergraduate Theses

    Browse

    All of Carroll ScholarsCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    DSpace software copyright © 2002-2023  DuraSpace
    DSpace Express is a service operated by 
    Atmire NV