Show simple item record

dc.contributor.authorChristenson, Chrisen_US
dc.contributor.authorKaikhah, Khosrowen_US
dc.date.accessioned2012-02-24T10:17:47Z
dc.date.available2012-02-24T10:17:47Z
dc.date.issued2006-02-01en_US
dc.identifier.citationChristenson, C. & Kaikhah, K. (2006). Incremental Evolution of Trainable Neural Networks that are Backwards Compatible. "Proceedings of the 5th IASTED International Conference on Artificial Intelligence and Applications (AIA)," pp. 222-227.
dc.identifier.urihttps://digital.library.txstate.edu/handle/10877/3809
dc.description.abstractSupervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully-connected layered design is often inadequate when performing such tasks. We demonstrate that evolution can be used to design an artificial neural network that learns faster and more accurately. By evolving artificial neural networks within a dynamic environment, the artificial neural network is forced to use learning. This strategy combined with incremental evolution produces an artificial neural network that outperforms the standard fully-connected layered design. The resulting artificial neural network can learn to perform an entire domain of tasks, including those of reduced complexity. Evolution alone can be used to create a network that performs a single task. However, real world environments are dynamic and thus require the ability to adapt to changes.en_US
dc.formatText
dc.format.extent6 pages
dc.format.medium1 file (.pdf)
dc.language.isoen_US
dc.sourceFifth IASTED International Conference on Artificial Intelligence and Applications (AIA), 2006, Innsbruck, Austria
dc.subjectIncremental evolutionen_US
dc.subjectNeural networksen_US
dc.subjectTrainingen_US
dc.subjectBackwards compatibleen_US
dc.titleIncremental Evolution of Trainable Neural Networks that are Backwards Compatibleen_US
txstate.documenttypeArticle
txstate.departmentComputer Science


Download

Thumbnail

This item appears in the following Collection(s)

Show simple item record