Multitask Visual Learning using Genetic Programming

by Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz Wieloch
Abstract:
We propose a multitask learning method of visual concepts within the genetic programming (GP) framework. Each GP individual is composed of several trees that process visual primitives derived from input images. Two trees solve two different visual tasks and are allowed to share knowledge with each other by commonly calling the remaining GP trees (subfunctions) included in the same individual. The performance of a particular tree is measured by its ability to reproduce the shapes contained in the training images. We apply this method to visual learning tasks of recognizing simple shapes and compare it to a reference method. The experimental verification demonstrates that such multitask learning often leads to performance improvements in one or both solved tasks, without extra computational effort.
Reference:
Multitask Visual Learning using Genetic Programming (Wojciech Jaśkowski, Krzysztof Krawiec, Bartosz Wieloch), In Evolutionary Computation, volume 16, 2008.
Bibtex Entry:
@Article{Jaskowski2008multitask,
  Title                    = {Multitask Visual Learning using Genetic Programming},
  Author                   = {Wojciech Jaśkowski and Krzysztof Krawiec and Bartosz Wieloch},
  Journal                  = {Evolutionary Computation},
  Year                     = {2008},
  Number                   = {4},
  Pages                    = {439-459},
  Volume                   = {16},

  Abstract                 = {We propose a multitask learning method of visual concepts within the genetic programming (GP) framework. Each GP individual is composed of several trees that process visual primitives derived from input images. Two trees solve two different visual tasks and are allowed to share knowledge with each other by commonly calling the remaining GP trees (subfunctions) included in the same individual. The performance of a particular tree is measured by its ability to reproduce the shapes contained in the training images. We apply this method to visual learning tasks of recognizing simple shapes and compare it to a reference method. The experimental verification demonstrates that such multitask learning often leads to performance improvements in one or both solved tasks, without extra computational effort.},
  Doi                      = {10.1162/evco.2008.16.4.439},
  Keywords                 = {multitask learning, genetic programming, visual learning, generative pattern recognition.}
}

This entry was posted by . Bookmark the permalink.