Krzysztof Krawiec


Home

Research:

edit SideBar

We consider multitask learning of visual concepts within genetic programming (GP) framework. The proposed method evolves a population of GP individuals, with each of them composed of several GP trees that process visual primitives derived from input images. The two main trees are delegated to solving two different visual tasks and are allowed to share knowledge with each other by calling the remaining GP trees (subfunctions) included in the same individual. The method is applied to the visual learning task of recognizing simple shapes, using generative approach based on visual primitives. We compare this approach to a reference method devoid of knowledge sharing, and conclude that in the worst case cross-task learning performs equally well, and in many cases it leads to significant performance improvements in one or both solved tasks.

@INPROCEEDINGS { Jaskowski07gecco,
    AUTHOR = { Wojciech Jaƛkowski and Krzysztof Krawiec and Bartosz Wieloch },
    TITLE = { Genetic Programming for Cross-task Knowledge Sharing },
    BOOKTITLE = { Genetic and Evolutionary Computation Conference GECCO },
    YEAR = { 2007 },
    EDITOR = { Dirk Thierens },
    PAGES = { 1620--1627 },
    PUBLISHER = { Association for Computing Machinery },
    ABSTRACT = { We consider multitask learning of visual concepts within genetic programming (GP) framework. The proposed method evolves a population of GP individuals, with each of them composed of several GP trees that process visual primitives derived from input images. The two main trees are delegated to solving two different visual tasks and are allowed to share knowledge with each other by calling the remaining GP trees (subfunctions) included in the same individual. The method is applied to the visual learning task of recognizing simple shapes, using generative approach based on visual primitives. We compare this approach to a reference method devoid of knowledge sharing, and conclude that in the worst case cross-task learning performs equally well, and in many cases it leads to significant performance improvements in one or both solved tasks. },
    ISBN = { 978-1-59593-698-1 },
    URL = { http://www.cs.put.poznan.pl/kkrawiec/pubs/p1620.pdf },
}


Powered by PmWiki