Evolving Simple Solutions to the CIFAR-10 Benchmark using Tangled Program Graphs
Created by W.Langdon from
gp-bibliography.bib Revision:1.7970
- @InProceedings{Smith:2021:CEC,
-
author = "Robert J. Smith and Ryan Amaral and
Malcolm I. Heywood",
-
booktitle = "2021 IEEE Congress on Evolutionary Computation (CEC)",
-
title = "Evolving Simple Solutions to the {CIFAR-10} Benchmark
using Tangled Program Graphs",
-
year = "2021",
-
editor = "Yew-Soon Ong",
-
pages = "2061--2068",
-
address = "Krakow, Poland",
-
month = "28 " # jun # "-1 " # jul,
-
isbn13 = "978-1-7281-8393-0",
-
abstract = "The goal of the CIFAR-10 benchmark is recast from the
perspective of discovering light-weight as well as
accurate solutions. Specifically, the image data, on
which CIFAR-10 is based, requires multiple practical
issues to be addressed that are not often considered
collectively when applying genetic programming to
classification problems. Issues of particular interest
include cardinality, multi-class classification and
diversity maintenance. We demonstrate that diversity
maintenance and cardinality can be approached
simultaneously by adopting a data subset to compose
pools of exemplars for lexicase selection. The issues
of multi-class classification and solution simplicity
are addressed by adopting the tangled program graph
(TPG) approach to emergent modularity. In addition, the
mutation operator is modified to ensure that class
labels do not 'die out' during evolution. The resulting
benchmarking study demonstrates solutions that are
significantly more accurate than AutoML while providing
comparable accuracies with solutions from unsupervised
feature discovery, i.e. 7percent accuracy. However,
unlike the latter TPG solutions are several orders of
magnitude simpler.",
-
keywords = "genetic algorithms, genetic programming, Training,
Sociology, Supervised learning, Training data,
Lighting, Benchmark testing, CIFAR-10, Tangled program
graphs, Modularity, Lexicase Selection, k-armed
Bandit",
-
DOI = "doi:10.1109/CEC45853.2021.9504998",
-
notes = "Also known as \cite{9504998}",
- }
Genetic Programming entries for
Robert J Smith
Ryan Amaral
Malcolm Heywood
Citations