Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4962255 | Procedia Computer Science | 2016 | 8 Pages |
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.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science (General)
Authors
Prasanna Date, James A. Hendler, Christopher D. Carothers,