Design Index for Deep Neural Networks
Authors
Date, Prasanna
Hendler, James A.
Carothers, Christopher D.
ORCID
No Thumbnail Available
Other Contributors
Issue Date
2016
Keywords
Degree
Terms of Use
Attribution-NonCommercial-NoDerivs 3.0 United States
Full Citation
P. Date, J. Hendler, and C. Carothers, Design Index for Deep Neural Networks, Procedia Computer Science, 88, 2016.
Abstract
In 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.
Description
Part 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
Department
Publisher
Elsevier