Created by W.Langdon from gp-bibliography.bib Revision:1.7615

- @Article{Nicolau:GPEM:funcset,
- author = "Miguel Nicolau and Alexandros Agapitos",
- title = "Choosing function sets with better generalisation performance for symbolic regression models",
- journal = "Genetic Programming and Evolvable Machines",
- year = "2021",
- volume = "22",
- number = "1",
- pages = "73--100",
- month = mar,
- keywords = "genetic algorithms, genetic programming, Symbolic regression, Machine learning, Generalisation, Overfitting, Data-driven modelling",
- ISSN = "1389-2576",
- DOI = "doi:10.1007/s10710-020-09391-4",
- abstract = "Supervised learning by means of Genetic Programming (GP) aims at the evolutionary synthesis of a model that achieves a balance between approximating the target function on the training data and generalising on new data. The model space searched by the Evolutionary Algorithm is populated by compositions of primitive functions defined in a function set. Since the target function is unknown, the choice of function set's constituent elements is primarily guided by the makeup of function sets traditionally used in the GP literature. Our work builds upon previous research of the effects of protected arithmetic operators (i.e. division, logarithm, power) on the output value of an evolved model for input data points not encountered during training. The scope is to benchmark the approximation/generalisation of models evolved using different function set choices across a range of 43 symbolic regression problems. The salient outcomes are as follows. Firstly, Koza's protected operators of division and exponentiation have a detrimental effect on generalisation, and should therefore be avoided. This result is invariant of the use of moderately sized validation sets for model selection. Secondly, the performance of the recently introduced analytic quotient operator is comparable to that of the sinusoidal operator on average, with their combination being advantageous to both approximation and generalisation. These findings are consistent across two different system implementations, those of standard expression-tree GP and linear Grammatical Evolution. We highlight that this study employed very large test sets, which create confidence when benchmarking the effect of different combinations of primitive functions on model generalisation. Our aim is to encourage GP researchers and practitioners to use similar stringent means of assessing generalisation of evolved models where possible, and also to avoid certain primitive functions that are known to be inappropriate.",
- notes = "College of Business, University College Dublin, Dublin, Ireland",
- }

Genetic Programming entries for Miguel Nicolau Alexandros Agapitos