Date of Award
3-2022
Document Type
Thesis
Degree Name
Master of Science
Department
Department of Operational Sciences
First Advisor
Lance E. Champagne, PhD
Abstract
Smoothing convolutional neural networks is investigated. When intermittent and random false predictions happen, a technique of average smoothing is applied to smooth out the incorrect predictions. While a simple problem environment shows proof of concept, obstacles remain for applying such a technique to a more operationally complex problem.
AFIT Designator
AFIT-ENS-MS-22-M-122
DTIC Accession Number
AD1170692
Recommended Citation
Drumm, Glen R., "Smoothing of Convolutional Neural Network Classifications" (2022). Theses and Dissertations. 5338.
https://scholar.afit.edu/etd/5338