Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology

A neural network classifier is sought. Classical neural network neurons are aggregations of a weight multiplied by an input value and then controlled via an activation function. This paper learns everything within the neuron using a variant of genetic programming called gene expression programming....

Full description

Bibliographic Details
Published in:2009 International Joint Conference on Neural Networks
Main Authors: Barton, Alan J., Valdes, Julio J., Orchard, Robert
Format: Article in Journal/Newspaper
Language:English
Published: IEEE 2009
Subjects:
Arctic
Online Access:https://doi.org/10.1109/IJCNN.2009.5178731
https://nrc-publications.canada.ca/eng/view/object/?id=be2de4a7-2607-4098-ac65-58bda4081cdd
https://nrc-publications.canada.ca/fra/voir/objet/?id=be2de4a7-2607-4098-ac65-58bda4081cdd
id ftnrccanada:oai:cisti-icist.nrc-cnrc.ca:cistinparc:23005057
record_format openpolar
spelling ftnrccanada:oai:cisti-icist.nrc-cnrc.ca:cistinparc:23005057 2023-05-15T15:00:17+02:00 Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology Barton, Alan J. Valdes, Julio J. Orchard, Robert 2009-07-31 text https://doi.org/10.1109/IJCNN.2009.5178731 https://nrc-publications.canada.ca/eng/view/object/?id=be2de4a7-2607-4098-ac65-58bda4081cdd https://nrc-publications.canada.ca/fra/voir/objet/?id=be2de4a7-2607-4098-ac65-58bda4081cdd eng eng IEEE 2009 International Joint Conference on Neural Networks, 2009 International Joint Conference on Neural Networks, IJCNN 2009, June 14-19, 2009, Atlanta, GA USA, ISBN: 978-1-4244-3548-7, Publication date: 2009-07-31, Pages: 264–271 doi:10.1109/IJCNN.2009.5178731 article 2009 ftnrccanada https://doi.org/10.1109/IJCNN.2009.5178731 2021-09-01T06:23:18Z A neural network classifier is sought. Classical neural network neurons are aggregations of a weight multiplied by an input value and then controlled via an activation function. This paper learns everything within the neuron using a variant of genetic programming called gene expression programming. That is, this paper does not explicitly use weights or activation functions within a neuron, nor bias nodes within a layer. Promising preliminary results are reported for a study of the detection of underground caves (a 1 class problem) and for a study of the interaction of water and minerals near a glacier in the Arctic (a 5 class problem). Peer reviewed: Yes NRC publication: Yes Article in Journal/Newspaper Arctic National Research Council Canada: NRC Publications Archive Arctic 2009 International Joint Conference on Neural Networks 264 271
institution Open Polar
collection National Research Council Canada: NRC Publications Archive
op_collection_id ftnrccanada
language English
description A neural network classifier is sought. Classical neural network neurons are aggregations of a weight multiplied by an input value and then controlled via an activation function. This paper learns everything within the neuron using a variant of genetic programming called gene expression programming. That is, this paper does not explicitly use weights or activation functions within a neuron, nor bias nodes within a layer. Promising preliminary results are reported for a study of the detection of underground caves (a 1 class problem) and for a study of the interaction of water and minerals near a glacier in the Arctic (a 5 class problem). Peer reviewed: Yes NRC publication: Yes
format Article in Journal/Newspaper
author Barton, Alan J.
Valdes, Julio J.
Orchard, Robert
spellingShingle Barton, Alan J.
Valdes, Julio J.
Orchard, Robert
Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
author_facet Barton, Alan J.
Valdes, Julio J.
Orchard, Robert
author_sort Barton, Alan J.
title Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
title_short Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
title_full Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
title_fullStr Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
title_full_unstemmed Learning the neuron functions within a neural network via Genetic Programming: applications to geophysics and hydrogeology
title_sort learning the neuron functions within a neural network via genetic programming: applications to geophysics and hydrogeology
publisher IEEE
publishDate 2009
url https://doi.org/10.1109/IJCNN.2009.5178731
https://nrc-publications.canada.ca/eng/view/object/?id=be2de4a7-2607-4098-ac65-58bda4081cdd
https://nrc-publications.canada.ca/fra/voir/objet/?id=be2de4a7-2607-4098-ac65-58bda4081cdd
geographic Arctic
geographic_facet Arctic
genre Arctic
genre_facet Arctic
op_relation 2009 International Joint Conference on Neural Networks, 2009 International Joint Conference on Neural Networks, IJCNN 2009, June 14-19, 2009, Atlanta, GA USA, ISBN: 978-1-4244-3548-7, Publication date: 2009-07-31, Pages: 264–271
doi:10.1109/IJCNN.2009.5178731
op_doi https://doi.org/10.1109/IJCNN.2009.5178731
container_title 2009 International Joint Conference on Neural Networks
container_start_page 264
op_container_end_page 271
_version_ 1766332388262019072

Similar Items