Evolutionary Discovery of Learning Rules for
Feedforward Neural Networks with Step Activation
Function
A. Radi, and R. Poli. Proceedings of the Genetic and Evolutionary
Computation Conference, 2, page 1178--1183. Orlando, Florida, USA, Morgan Kaufmann, (13-17 July 1999)
Neural networks with step activation function can be
very efficient ways of performing non linear mappings.
However, no standard learning algorithm exists for
training this kind of neural networks. In this work we
use Genetic Programming (GP) to discover supervised
learning algorithms which can train neural networks
with step activation function. Thanks to GP, a new
learning algorithm has been discovered which has been
shown to provide good performance.(more)
Proceedings of the Genetic and Evolutionary
Computation Conference
year
1999
month
13-17 July
pages
1178--1183
publisher
Morgan Kaufmann
volume
2
publisher_address
San Francisco, CA 94104, USA
isbn
1-55860-611-4
notes
GECCO-99 A joint meeting of the eighth international
conference on genetic algorithms (ICGA-99) and the
fourth annual genetic programming conference (GP-99)
Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Conference Paper
%1 radi:1999:EDLRFNNSAF
%A Radi, Amr
%A Poli, Riccardo
%B Proceedings of the Genetic and Evolutionary
Computation Conference
%C Orlando, Florida, USA
%D 1999
%E Banzhaf, Wolfgang
%E Daida, Jason
%E Eiben, Agoston E.
%E Garzon, Max H.
%E Honavar, Vasant
%E Jakiela, Mark
%E Smith, Robert E.
%I Morgan Kaufmann
%K algorithms, and evolvable genetic hardware programming
%P 1178--1183
%T Evolutionary Discovery of Learning Rules for
Feedforward Neural Networks with Step Activation
Function
%U http://www.cs.bham.ac.uk/~wbl/biblio/gecco1999/GP-428.attempt2.ps
%V 2
%X Neural networks with step activation function can be
very efficient ways of performing non linear mappings.
However, no standard learning algorithm exists for
training this kind of neural networks. In this work we
use Genetic Programming (GP) to discover supervised
learning algorithms which can train neural networks
with step activation function. Thanks to GP, a new
learning algorithm has been discovered which has been
shown to provide good performance.
%@ 1-55860-611-4
@inproceedings{radi:1999:EDLRFNNSAF,
abstract = {Neural networks with step activation function can be
very efficient ways of performing non linear mappings.
However, no standard learning algorithm exists for
training this kind of neural networks. In this work we
use Genetic Programming (GP) to discover supervised
learning algorithms which can train neural networks
with step activation function. Thanks to GP, a new
learning algorithm has been discovered which has been
shown to provide good performance.},
added-at = {2008-06-19T17:46:40.000+0200},
address = {Orlando, Florida, USA},
author = {Radi, Amr and Poli, Riccardo},
biburl = {https://www.bibsonomy.org/bibtex/2c9ddc169f30f95f9a498f5b2366ed5e3/brazovayeye},
booktitle = {Proceedings of the Genetic and Evolutionary
Computation Conference},
editor = {Banzhaf, Wolfgang and Daida, Jason and Eiben, Agoston E. and Garzon, Max H. and Honavar, Vasant and Jakiela, Mark and Smith, Robert E.},
interhash = {4402d2311997dd34232a39293cdeb680},
intrahash = {c9ddc169f30f95f9a498f5b2366ed5e3},
isbn = {1-55860-611-4},
keywords = {algorithms, and evolvable genetic hardware programming},
month = {13-17 July},
notes = {GECCO-99 A joint meeting of the eighth international
conference on genetic algorithms (ICGA-99) and the
fourth annual genetic programming conference (GP-99)},
pages = {1178--1183},
publisher = {Morgan Kaufmann},
publisher_address = {San Francisco, CA 94104, USA},
timestamp = {2008-06-19T17:50:01.000+0200},
title = {Evolutionary Discovery of Learning Rules for
Feedforward Neural Networks with Step Activation
Function},
url = {http://www.cs.bham.ac.uk/~wbl/biblio/gecco1999/GP-428.attempt2.ps},
volume = 2,
year = 1999
}