Date of Award

5-30-2019

Document Type

Thesis

Degree Name

Bachelor of Science (B.S.) in Computer Science and University Honors

Department

Computer Science

First Advisor

Melanie Mitchell

Subjects

Machine learning, Neural networks, Computer vision, Image processing -- Digital techniques, Transfer learning

DOI

10.15760/honors.716

Abstract

Pretrained models could be reused in a way that allows for improvement in training accuracy. Training a model from scratch takes time. The goal is improving accuracy and minimizing the loss across individual epochs. The hypothesis is that transfer learning could potentially improve on the rate of accuracy and speed of training per epoch iteration.

Persistent Identifier

https://archives.pdx.edu/ds/psu/28828

Share

COinS