Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLane, PCR-
dc.contributor.authorGobet, F-
dc.identifier.citationProceedings of the ICML-2005 Workshop on Meta-learning.en
dc.description.abstractExploring multiple classes of learning algorithms for those algorithms which perform best in multiple tasks is a complex problem of multiple-criteria optimisation. We use a genetic algorithm to locate sets of models which are not outperformed on all of the tasks. The genetic algorithm develops a population of multiple types of learning algorithms, with competition between individuals of different types. We find that inherent differences in the convergence time and performance levels of the different algorithms leads to misleading population effects. We explore the role that the algorithm representation and initial population has on task performance. Our findings suggest that separating the representation of different algorithms is beneficial in enhancing performance. Also, initial seeding is required to avoid premature convergence to non-optimal classes of algorithms.en
dc.format.extent136903 bytes-
dc.publisherProceedings of the ICML-2005 Workshop on Meta-learningen
dc.subjectTheory developmenten
dc.subjectLearning algorithmen
dc.subjectConcept formationen
dc.subjectMathematical modelen
dc.titleMulti-task learning and transfer: The effect of algorithm representationen
dc.typeResearch Paperen
Appears in Collections:Psychology
Dept of Life Sciences Research Papers

Files in This Item:
File Description SizeFormat 
lane-icml05.pdf133.69 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.