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

R. Neville, S. Holland

    Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
    Title of host publicationProceedings of the International Joint Conference on Neural Networks|Proc Int Jt Conf Neural Networks
    Place of PublicationUSA
    PublisherIEEE
    Pages30-37
    Number of pages7
    ISBN (Print)9781424418213
    DOIs
    Publication statusPublished - 2008
    Event2008 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

    Conference2008 International Joint Conference on Neural Networks, IJCNN 2008
    CityHong Kong
    Period1/07/08 → …
    Internet address

    Fingerprint

    Dive into the research topics of 'Generating weights and generating vectors to map complex functions with artificial neural networks'. Together they form a unique fingerprint.

    Cite this