Artificial neural network development by means of a novel combination of grammatical evolution and genetic algorithm
Created by W.Langdon from
gp-bibliography.bib Revision:1.8081
- @Article{journals/eaai/AhmadizarSAT15,
-
author = "Fardin Ahmadizar and Khabat Soltanian and
Fardin AkhlaghianTab and Ioannis Tsoulos",
-
title = "Artificial neural network development by means of a
novel combination of grammatical evolution and genetic
algorithm",
-
journal = "Engineering Applications of Artificial Intelligence",
-
year = "2015",
-
volume = "39",
-
bibdate = "2015-02-23",
-
bibsource = "DBLP,
http://dblp.uni-trier.de/db/journals/eaai/eaai39.html#AhmadizarSAT15",
-
pages = "1--13",
-
month = mar,
-
keywords = "genetic algorithms, genetic programming, grammatical
evolution, Neural networks, ANN, Adaptive penalty
approach, Classification problems",
-
ISSN = "0952-1976",
-
URL = "http://www.sciencedirect.com/science/article/pii/S0952197614002759",
-
URL = "http://dx.doi.org/10.1016/j.engappai.2014.11.003",
-
abstract = "The most important problems with exploiting artificial
neural networks (ANNs) are to design the network
topology, which usually requires an excessive amount of
expert's effort, and to train it. In this paper, a new
evolutionary-based algorithm is developed to
simultaneously evolve the topology and the connection
weights of ANNs by means of a new combination of
grammatical evolution (GE) and genetic algorithm (GA).
GE is adopted to design the network topology while GA
is incorporated for better weight adaptation. The
proposed algorithm needs to invest a minimal expert's
effort for customisation and is capable of generating
any feedforward ANN with one hidden layer. Moreover,
due to the fact that the generalisation ability of an
ANN may decrease because of over fitting problems, the
algorithm uses a novel adaptive penalty approach to
simplify ANNs generated through the evolution process.
As a result, it produces much simpler ANNs that have
better generalization ability and are easy to
implement. The proposed method is tested on some real
world classification datasets, and the results are
statistically compared against existing methods in the
literature. The results indicate that our algorithm
outperforms the other methods and provides the best
overall performance in terms of the classification
accuracy and the number of hidden neurons. The results
also present the contribution of the proposed penalty
approach in the simplicity and generalisation ability
of the generated networks.",
-
notes = "also known as \cite{AHMADIZAR20151}",
- }
Genetic Programming entries for
Fardin Ahmadizar
Khabat Soltanian
Fardin Akhlaghian Tab
Ioannis G Tsoulos
Citations