Machine Learning - Special issue on inductive transfer
ICES '96 Proceedings of the First International Conference on Evolvable Systems: From Biology to Hardware
Evolving Modules in Genetic Programming by Subtree Encapsulation
EuroGP '01 Proceedings of the 4th European Conference on Genetic Programming
Collective adaptation: the sharing of building blocks
Collective adaptation: the sharing of building blocks
Improved Rooftop Detection in Aerial Images with Machine Learning
Machine Learning
Pattern Recognition Letters - Special issue: Evolutionary computer vision and image understanding
Knowledge reuse in genetic programming applied to visual learning
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Learning and Recognition of Hand-Drawn Shapes Using Generative Genetic Programming
Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing
Learning high-level visual concepts using attributed primitives and genetic programming
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
Evolving pattern recognition systems
IEEE Transactions on Evolutionary Computation
Visual learning by coevolutionary feature synthesis
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Knowledge reuse in genetic programming applied to visual learning
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Generative learning of visual concepts using multiobjective genetic programming
Pattern Recognition Letters
Genetic Programming and Evolvable Machines
Hi-index | 0.00 |
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.