We propose a multitask learning method of visual concepts within the genetic program- ming (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 remain- ing 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 train- ing 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.
@ARTICLE { jaskowski08ec,
AUTHOR = { Wojciech Ja\'skowski and Krzysztof Krawiec and Bartosz Wieloch },
TITLE = { Multitask Visual Learning using Genetic Programming },
JOURNAL = { Evolutionary Computation },
YEAR = { 2008 },
VOLUME = { 16 },
PAGES = { 439--459 },
NUMBER = { 4 },
ABSTRACT = { We propose a multitask learning method of visual concepts within the genetic program- ming (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 remain- ing 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 train- ing 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. },
COMMENT = { ProjectELP },
PUBLISHER = { {MIT} Press },
}