A Bayesian Evolutionary Approach to the Design and Learning of Heterogeneous Neural Trees
Created by W.Langdon from
gp-bibliography.bib Revision:1.8051
- @Article{Zhang:2002:ICAE,
-
author = "Byoung-Tak Zhang",
-
title = "A {Bayesian} Evolutionary Approach to the Design and
Learning of Heterogeneous Neural Trees",
-
journal = "Integrated Computer-Aided Engineering",
-
year = "2002",
-
volume = "9",
-
number = "1",
-
pages = "73--86",
-
month = jan,
-
keywords = "genetic algorithms, genetic programming",
-
broken = "http://iospress.metapress.com/openurl.asp?genre=article&issn=1069-2509&volume=9&issue=1&spage=73",
-
URL = "https://bi.snu.ac.kr/Publications/Journals/International/ICAE9_1.pdf",
-
DOI = "doi:10.3233/ICA-2002-9105",
-
size = "14 pages",
-
abstract = "Evolutionary algorithms have been successfully applied
to the design and training of neural networks, such as
in optimisation of network architecture, learning
connection weights, and selecting training data. While
most of existing evolutionary methods are focused on
one of these aspects, we present in this paper an
integrated approach that employs evolutionary
mechanisms for the optimisation of these components
simultaneously. This approach is especially effective
when evolving irregular, not-strictly-layered networks
of heterogeneous neurons with variable receptive
fields. The core of our method is the neural tree
representation scheme combined with the Bayesian
evolutionary learning framework. The generality and
flexibility of neural trees make it easy to express and
modify complex neural architectures by means of
standard crossover and mutation operators. The Bayesian
evolutionary framework provides a theoretical
foundation for finding compact neural networks using a
small data set by principled exploitation of background
knowledge available in the problem domain. Performance
of the presented method is demonstrated on a suite of
benchmark problems and compared with those of related
methods.",
- }
Genetic Programming entries for
Byoung-Tak Zhang
Citations