Evolving Simpler Constructed Features for Clustering Problems with Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.7954
- @InProceedings{Schofield:2020:CEC,
-
author = "Finn Schofield and Andrew Lensen",
-
title = "Evolving Simpler Constructed Features for Clustering
Problems with Genetic Programming",
-
booktitle = "2020 IEEE Congress on Evolutionary Computation, CEC
2020",
-
year = "2020",
-
editor = "Yaochu Jin",
-
pages = "paper id24602",
-
address = "internet",
-
month = "19-24 " # jul,
-
organization = "IEEE Computational Intelligence Society",
-
publisher = "IEEE Press",
-
keywords = "genetic algorithms, genetic programming, Clustering,
Feature Construction, Parsimony Pressure, Feature
Selection, k-means",
-
isbn13 = "978-1-7281-6929-3",
-
URL = "https://www.andrewlensen.com/files/schofield2020evolving.pdf",
-
DOI = "doi:10.1109/CEC48606.2020.9185575",
-
size = "8 pages",
-
abstract = "Clustering is a widely used unsupervised learning
technique. However, as the size and complexity of data
increases, the performance of clustering algorithms
diminishes, as well as the interpretability of the
clustering partition. Genetic programming has been used
to perform feature construction on data to increase
clustering performance. However, existing work has not
focused on encouraging simpler constructed features.
existing techniques are further developed to include
parsimony pressure, a method to encourage evolution
towards simpler solutions. With simpler solutions, the
constructed features become easier to understand and
interpret. The results of experiments using the
proposed method show that parsimony pressure is an
effective method for producing significantly simpler
constructed features without any reduction on the
performance of k-means++ clustering. Evolved
individuals are also analysed to demonstrate the effect
of parsimony pressure on interpretability, showing the
power of parsimony pressure for avoiding redundancies
in individuals, and thus increasing the
interpretability",
-
notes = "https://wcci2020.org/
Victoria University of Wellington, New Zealand.
Also known as \cite{9185575}",
- }
Genetic Programming entries for
Finn Schofield
Andrew Lensen
Citations