Design Index for Deep Neural Networks
AuthorDate, Prasanna; Hendler, James A.; Carothers, Christopher D.
Full CitationP. Date, J. Hendler, and C. Carothers, Design Index for Deep Neural Networks, Procedia Computer Science, 88, 2016.
MetadataShow full item record
URIhttps://doi.org/10.1016/j.procs.2016.07.416; https://www.sciencedirect.com/science/article/pii/S1877050916316726; https://hdl.handle.net/20.500.13015/6415
AbstractIn this paper, we propose a Deep Neural Networks (DNN) Design Index which would aid a DNN designer during the designing phase of DNNs. We study the designing aspect of DNNs from model-specific and data-specific perspectives with focus on three performance metrics: training time, training error and, validation error. We use a simple example to illustrate the significance of the DNN design index. To validate it, we calculate the design indices for four benchmark problems. This is an elementary work aimed at setting a direction for creating design indices pertaining to deep learning.;
DescriptionPart of special issue: 7th Annual International Conference on Biologically Inspired Cognitive Architectures, BICA 2016, held July 16 to July 19, 2016 in New York City, NY, USA
The following license files are associated with this item: