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....
Published in: | 2009 International Joint Conference on Neural Networks |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2009
|
Subjects: | |
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 |
Summary: | 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 |
---|