Learning feature spaces for regression with genetic programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.7970
- @Article{LaCava:GPEM,
-
author = "William {La Cava} and Jason H. Moore",
-
title = "Learning feature spaces for regression with genetic
programming",
-
journal = "Genetic Programming and Evolvable Machines",
-
year = "2020",
-
volume = "21",
-
number = "3",
-
pages = "433--467",
-
month = sep,
-
note = "Special Issue: Highlights of Genetic Programming 2019
Events",
-
keywords = "genetic algorithms, genetic programming, FEAT, ANN,
Representation learning, Feature construction,
Variation, Regression",
-
ISSN = "1389-2576",
-
DOI = "doi:https://doi.org/10.1007/s10710-020-09383-4",
-
size = "35 pages",
-
abstract = "Genetic programming has found recent success as a tool
for learning sets of features for regression and
classification. Multidimensional genetic programming is
a useful variant of genetic programming for this task
because it represents candidate solutions as sets of
programs. These sets of programs expose additional
information that can be exploited for building block
identification. In this work, we discuss this
architecture and others in terms of their propensity
for allowing heuristic search to use information during
the evolutionary process. We investigate methods for
biasing the components of programs that are promoted in
order to guide search towards useful and complementary
feature spaces. We study two main approaches: (1) the
introduction of new objectives and (2) the use of
specialized semantic variation operators. We find that
a semantic crossover operator based on stagewise
regression leads to significant improvements on a set
of regression problems. The inclusion of semantic
crossover produces state-of-the-art machine learning
approaches and other genetic programming frameworks.
Finally, we look at the collinearity and complexity of
the data representations produced by different methods,
in order to assess whether relevant, concise, and
independent factors of variation can be produced in
application.",
-
notes = "Random Forest, ElasticNet SGD, Lasso, LinSVR, LinReg,
KernelRidge, GradBoost, XGBoost, MLP, RF, Adaboost,
GSGP, AFP, EPLEX, Feat, EPLEX-1M, MRGP, FeatResXO,
FeatStageXO",
- }
Genetic Programming entries for
William La Cava
Jason H Moore
Citations