Dissecting Convolutional Neural Networks

Thumbnail Image

Files

WHITAKER-HONORSTHESIS-2018.pdf (485.16 KB)

Date

2019-06-12

Authors

Whitaker, Justin Daniel

Journal Title

Journal ISSN

Volume Title

Publisher

East Carolina University

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.

Description

Keywords

machine learning , neural network , convolutional , supervised learning

Citation

URI

http://hdl.handle.net/10342/7293

Collections

Honors College