Abstract
Genetic Programming (GP) for symbolic regression often generates over-complex models, which overfit the training data and have poor generalization onto unseen data. One recent work investigated controlling model complexity by using a new GP representation called Adaptive Weighted Splines (AWS), which is a semi-structured representation that can control the model complexity explicitly. This work extends this previous work by incorporating a new parsimony pressure objective to further control the model complexity. Experimental results demonstrate that the new multi-objective GP method consistently obtains superior fronts and produces better generalizing models compared to single-objective GP with both the tree-based and AWS representation as well a multi-objective tree-based GP method with parsimony pressure.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
