Cross-task code reuse in genetic programming applied to visual learning

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{journals/amcs/JaskowskiKW14,
  title =        "Cross-task code reuse in genetic programming applied
                 to visual learning",
  author =       "Wojciech Jaskowski and Krzysztof Krawiec and 
                 Bartosz Wieloch",
  journal =      "Applied Mathematics and Computer Science",
  year =         "2014",
  number =       "1",
  volume =       "24",
  pages =        "183--197",
  keywords =     "genetic algorithms, genetic programming, code reuse,
                 knowledge sharing, visual learning, multi-task
                 learning, optical character recognition",
  bibdate =      "2014-05-05",
  bibsource =    "DBLP,
                 http://dblp.uni-trier.de/db/journals/amcs/amcs24.html#JaskowskiKW14",
  URL =          "http://dx.doi.org/10.2478/amcs-2014-0014",
  abstract =     "We propose a method that enables effective code reuse
                 between evolutionary runs that solve a set of related
                 visual learning tasks. We start with introducing a
                 visual learning approach that uses genetic programming
                 individuals to recognise objects. The process of
                 recognition is generative, i.e., requires the learner
                 to restore the shape of the processed object. This
                 method is extended with a code reuse mechanism by
                 introducing a crossbreeding operator that allows
                 importing the genetic material from other evolutionary
                 runs. In the experimental part, we compare the
                 performance of the extended approach to the basic
                 method on a real-world task of handwritten character
                 recognition, and conclude that code reuse leads to
                 better results in terms of fitness and recognition
                 accuracy. Detailed analysis of the crossbred genetic
                 material shows also that code reuse is most profitable
                 when the recognised objects exhibit visual similarity",
}

Genetic Programming entries for Wojciech Jaskowski Krzysztof Krawiec Bartosz Wieloch

Citations