@brazovayeye

Genetic programming for cross-task knowledge sharing

, , and . GECCO '07: Proceedings of the 9th annual conference on Genetic and evolutionary computation, 2, page 1620--1627. London, ACM Press, (7-11 July 2007)

Abstract

We consider multi-task 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 (sub-functions) included in the same individual. The method is applied to the visual learning task of recognising simple shapes, using generative approach based on visual primitives, introduced in 17. 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.

Links and resources

Tags

community