Impacts of Sample Design for Validation Data on the Accuracy of Feedforward Neural Network Classification
Validation data are often used to evaluate the performance of a trained neural network and used in the selection of a network deemed optimal for the task at-hand. Optimality is commonly assessed with a measure, such as overall classification accuracy. The latter is often calculated directly from a c...
Main Author: | Giles M. Foody |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-08-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/7/9/888 |
Similar Items
-
The Sample Size Influence in the Accuracy of the Image Classification of the Remote Sensing
by: Thomaz C. e C. da Costa, et al.
Published: (2004-12-01) -
The Sensitivity of Mapping Methods to Reference Data Quality: Training Supervised Image Classifications with Imperfect Reference Data
by: Giles M. Foody, et al.
Published: (2016-11-01) -
Application of Optimized SVM in Sample Classification
by: Yao, X.
Published: (2022) -
Trends in Remote Sensing Accuracy Assessment Approaches in the Context of Natural Resources
by: Lucia Morales-Barquero, et al.
Published: (2019-10-01) -
On Accuracy of PDF Divergence Estimators and Their Applicability to Representative Data Sampling
by: Katarzyna Musial, et al.
Published: (2011-07-01)