INDIGO Home University of Illinois at Urbana-Champaign logo uic building uic pavilion uic student center

On the Use of Deep Boltzmann Machines for Road Signs Classification

Show full item record

Bookmark or cite this item:

Files in this item

File Description Format
PDF DEramo_Carlo.pdf (19MB) (no description provided) PDF
Title: On the Use of Deep Boltzmann Machines for Road Signs Classification
Author(s): D'Eramo, Carlo
Advisor(s): Ziebart, Brian
Contributor(s): Berger-Wolf, Tanya; Zanero, Stefano
Department / Program: Computer Science
Graduate Major: Computer Science
Degree Granting Institution: University of Illinois at Chicago
Degree: MS, Master of Science
Genre: Masters
Subject(s): machine learning generative models deep boltzmann machine complex objects recognition
Abstract: The Deep Boltzmann Machine (DBM) has been proved to be one of the most effective machine learning generative models in discriminative tasks. They've been able to overcome other generative, and even discriminative models, on relatively simple tasks, such as digits recognition, and also on more complex tasks such as simple objects recognition. However, there're only a few published results of DBM performances on other complex datasets. In this work we decided to test the efficiency of DBM, and its variant Multi-Prediction Deep Boltzmann Machine (MP-DBM), in classifying a complex dataset composed of road signs and we'll show how we've been able to train both models to reach what, at the best of our knowledge, are the best discriminative results of generative models on the road signs dataset.
Issue Date: 2015-10-21
Genre: thesis
Rights Information: Copyright 2015 Carlo D'Eramo
Date Available in INDIGO: 2015-10-21
Date Deposited: 2015-08

This item appears in the following Collection(s)

Show full item record


Country Code Views
United States of America 99
China 61
Ukraine 21
Russian Federation 18
Germany 7


My Account


Access Key