Dissecting Convolutional Neural Networks
Author
Whitaker, Justin Daniel
Abstract
I examined the hidden layers of a convolutional neural network for MNIST handwritten digit classification. I found that it is possible to view how backpropagation affects nodes in the activation maps of hidden layers by visualizing their outputs as images across training epochs. This can allow one to look inside the black box of neural networks and to gain a deeper understanding of their mechanics.
Date
2019-06-12
Citation:
APA:
Whitaker, Justin Daniel.
(June 2019).
Dissecting Convolutional Neural Networks
(Honors Thesis, East Carolina University). Retrieved from the Scholarship.
(http://hdl.handle.net/10342/7293.)
MLA:
Whitaker, Justin Daniel.
Dissecting Convolutional Neural Networks.
Honors Thesis. East Carolina University,
June 2019. The Scholarship.
http://hdl.handle.net/10342/7293.
September 25, 2023.
Chicago:
Whitaker, Justin Daniel,
“Dissecting Convolutional Neural Networks”
(Honors Thesis., East Carolina University,
June 2019).
AMA:
Whitaker, Justin Daniel.
Dissecting Convolutional Neural Networks
[Honors Thesis]. Greenville, NC: East Carolina University;
June 2019.
Collections
Publisher
East Carolina University