Dissecting Convolutional Neural Networks

dc.access.option	Open Access
dc.contributor.advisor	Ding, Junhua
dc.contributor.author	Whitaker, Justin Daniel
dc.contributor.department	Computer Science
dc.date.accessioned	2019-06-18T13:25:48Z
dc.date.available	2019-06-18T13:25:48Z
dc.date.created	2018-05
dc.date.issued	2019-06-12
dc.date.submitted	May 2018
dc.date.updated	2019-06-14T13:22:41Z
dc.degree.department	Computer Science
dc.degree.discipline	Computer Science
dc.degree.grantor	East Carolina University
dc.degree.level	Undergraduate
dc.degree.name	BS
dc.description.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.
dc.format.mimetype	application/pdf
dc.identifier.uri	http://hdl.handle.net/10342/7293
dc.publisher	East Carolina University
dc.subject	machine learning
dc.subject	neural network
dc.subject	convolutional
dc.subject	supervised learning
dc.title	Dissecting Convolutional Neural Networks
dc.type	Honors Thesis
dc.type.material	text

Files

Now showing 1 - 1 of 1