Date of Award
Bachelor of Science (B.S.) in Computer Science and University Honors
Machine learning, Neural networks, Computer vision, Image processing -- Digital techniques, Transfer learning
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.
Le, Jordan T., "The Improvement of Machine Learning Accuracies through Transfer Learning" (2019). University Honors Theses. Paper 699.