Skip navigation
Please use this identifier to cite or link to this item:
Title: An Empirical Evaluation of Deep Architecture Classification Using Simulated Datasets
Authors: Khore, Karthik
Advisors: Liu, Han
Department: Operations Research and Financial Engineering
Class Year: 2015
Abstract: I present an empirical evaluation of deep architectures used for supervised learning and classification. Deep learning methods have recently become a popular topic, which many researchers have claimed to have better performance on complicated vision datasets. So far, comparisons of deep architectures with other classical methods only utilize the MNIST dataset of handwritten digits (and permutations thereof) to evaluate their performance. In this thesis, I expand this evaluation of deep learning methods by generating datasets with varying size, dimension, number of classes, and distribution to fully stress these methods across a variety of datasets. From these tests, I find that deep learning methods have equal performance or, in some cases, worse performance than classical methods on certain datasets.
Extent: 63 pages
Type of Material: Princeton University Senior Theses
Language: en_US
Appears in Collections:Operations Research and Financial Engineering, 2000-2017

Files in This Item:
File SizeFormat 
PUTheses2015-Khore_Karthik.pdf567.56 kBAdobe PDF    Request a copy

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