Generating weights and generating vectors to map complex functions with artificial neural networks

R. Neville; S. Holland

doi:10.1109/IJCNN.2008.4633763

Generating weights and generating vectors to map complex functions with artificial neural networks

R. Neville, S. Holland

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The generation of weights is an alternative method of loading a set of weights into an artificial neural network. It is a process that transforms a trained base net by multiplying its weights by symmetric matrices [1]. These weights are then assigned to a derived net. The derived nets map symmetrically related functions. At present, the process is limited because it cannot be applied to one-to-many functions. In this paper, this limitation is overcome by generating a set of vectors from the transformed derived nets that are then used to train an ANN to map one-to-many tasks. The associated rotational symmetries performed are also specified. © 2008 IEEE.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks\|Proc Int Jt Conf Neural Networks
Place of Publication	USA
Publisher	IEEE
Pages	30-37
Number of pages	7
ISBN (Print)	9781424418213
DOIs	https://doi.org/10.1109/IJCNN.2008.4633763
Publication status	Published - 2008
Event	2008 International Joint Conference on Neural Networks, IJCNN 2008 - Hong Kong Duration: 1 Jul 2008 → … http://dblp.uni-trier.de/db/conf/ijcnn/ijcnn2008.html#RastYKF08http://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08.xmlhttp://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08

Conference

Conference	2008 International Joint Conference on Neural Networks, IJCNN 2008
City	Hong Kong
Period	1/07/08 → …
Internet address	http://dblp.uni-trier.de/db/conf/ijcnn/ijcnn2008.html#RastYKF08http://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08.xmlhttp://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08

Access to Document

10.1109/IJCNN.2008.4633763

Cite this

@inproceedings{451998d3f0024a7d9fae99861a25c2d3,

title = "Generating weights and generating vectors to map complex functions with artificial neural networks",

abstract = "The generation of weights is an alternative method of loading a set of weights into an artificial neural network. It is a process that transforms a trained base net by multiplying its weights by symmetric matrices [1]. These weights are then assigned to a derived net. The derived nets map symmetrically related functions. At present, the process is limited because it cannot be applied to one-to-many functions. In this paper, this limitation is overcome by generating a set of vectors from the transformed derived nets that are then used to train an ANN to map one-to-many tasks. The associated rotational symmetries performed are also specified. {\textcopyright} 2008 IEEE.",

author = "R. Neville and S. Holland",

year = "2008",

doi = "10.1109/IJCNN.2008.4633763",

language = "English",

isbn = "9781424418213",

pages = "30--37",

booktitle = "Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks",

publisher = "IEEE",

address = "United States",

note = "2008 International Joint Conference on Neural Networks, IJCNN 2008 ; Conference date: 01-07-2008",

url = "http://dblp.uni-trier.de/db/conf/ijcnn/ijcnn2008.html#RastYKF08http://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08.xmlhttp://dblp.uni-trier.de/rec/bibtex/conf/ijcnn/RastYKF08",

}

Neville, R & Holland, S 2008, Generating weights and generating vectors to map complex functions with artificial neural networks. in Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks. IEEE, USA, pp. 30-37, 2008 International Joint Conference on Neural Networks, IJCNN 2008, Hong Kong, 1/07/08. https://doi.org/10.1109/IJCNN.2008.4633763

TY - GEN

T1 - Generating weights and generating vectors to map complex functions with artificial neural networks

AU - Neville, R.

AU - Holland, S.

PY - 2008

Y1 - 2008

N2 - The generation of weights is an alternative method of loading a set of weights into an artificial neural network. It is a process that transforms a trained base net by multiplying its weights by symmetric matrices [1]. These weights are then assigned to a derived net. The derived nets map symmetrically related functions. At present, the process is limited because it cannot be applied to one-to-many functions. In this paper, this limitation is overcome by generating a set of vectors from the transformed derived nets that are then used to train an ANN to map one-to-many tasks. The associated rotational symmetries performed are also specified. © 2008 IEEE.

AB - The generation of weights is an alternative method of loading a set of weights into an artificial neural network. It is a process that transforms a trained base net by multiplying its weights by symmetric matrices [1]. These weights are then assigned to a derived net. The derived nets map symmetrically related functions. At present, the process is limited because it cannot be applied to one-to-many functions. In this paper, this limitation is overcome by generating a set of vectors from the transformed derived nets that are then used to train an ANN to map one-to-many tasks. The associated rotational symmetries performed are also specified. © 2008 IEEE.

U2 - 10.1109/IJCNN.2008.4633763

DO - 10.1109/IJCNN.2008.4633763

M3 - Conference contribution

SN - 9781424418213

SP - 30

EP - 37

BT - Proceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks

PB - IEEE

CY - USA

T2 - 2008 International Joint Conference on Neural Networks, IJCNN 2008

Y2 - 1 July 2008

ER -

Generating weights and generating vectors to map complex functions with artificial neural networks

Abstract

Conference

Access to Document

Fingerprint

Cite this