Abstract
We propose a new type of leaf node for use in Symbolic Regression (SR) that performs linear combinations of feature variables (LCF). LCF's weights are tuned using a gradient method based on back-propagation algorithm known from neural networks. Multi-Gene Genetic Programming (MGGP) was chosen as a baseline model. As a sanity check, we experimentally show that LCFs improve the performance of the baseline on a rotated toy SR problem. We then perform a thorougher experimental study on a number of artificial and real-world SR benchmarks. The usage of LCFs in MGGP statically improved the results in 5 cases out of 9, while it worsen them in only a single case.
Sign-in/Register to access full text options 
Free) 
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 call
