Skip navigation
Please use this identifier to cite or link to this item:
Title: An Investigation of Convolutional Neural Networks
Authors: Hancock, Brannan
Advisors: Ramadge, Peter
Contributors: Verma, Naveen
Department: Electrical Engineering
Class Year: 2016
Abstract: This report documents the process of creating a Convolutional Neural Network from basis in Matlab. Convolution, Fully Connected, Average Pooling, Max Pooling, Rectifying, Softmax and Cross Entropy Layers were implemented as Object Classes. This allows construction of Convolutional Neural Networks with arbitrary topology comprised of such layers. Experiments verifying that the features learnt by the Convolutional Neural Networks are what allows them to improve upon Neural Network Classifiers were carried out and detailed. The redundancy in the output of the Convolutional Neural Network was examined, and revealed that reducing such a Networks output to as few as eight of its principle components still contains enough information to correctly classify handwritten digits with a precision of 92.09%. Finally the effect of choosing between Average and Max pooling was explored, revealing Max Pooling tends to lead to more precise classifiers.
Extent: 152 pages
Type of Material: Princeton University Senior Theses
Language: en_US
Appears in Collections:Electrical Engineering, 1932-2017

Files in This Item:
File SizeFormat 
Brannan_Hancock_Thesis.pdf1.53 MBAdobe PDF    Request a copy

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.