elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Optimierung eines neuronalen Netzes zur Objekterkennung unter Verwendung evolutionärer Algorithmen

Kornfeld, Nils (2017) Optimierung eines neuronalen Netzes zur Objekterkennung unter Verwendung evolutionärer Algorithmen. Master's, Freie Universität Berlin.

[img] PDF
2MB

Official URL: http://www.mi.fu-berlin.de/inf/groups/ag-ki/Theses/Completed-theses/Master_Diploma-theses/2017/Kornfeld/index.html

Abstract

In recent years, neural networks have been widely used as the method of choice for classification tasks in computer vision and image processing. The networks that currently provide the best results are very deep residual Convolutional Neural Networks. New network structures, based on the previously used topologies are developed each year, using different approaches. In this thesis the application of a canonical genetic algorithm to optimize the topology of neural networks is investigated. Current state of the art networks are used as a baseline to start the optimization form. The generated architectures achieve an improved classification accuracy, compared to reference networks. The developed network structures differ from commonly used architectures in their higher level architecture. In contrast to the reference networks they are not homogeneously from a sequence of different blocks. The improved classification accuracy suggests that the use of heterogeneous structures may be advantageous. Furthermore it is shown that the generated neural networks converge in fewer iterations, producing better results.

Item URL in elib:https://elib.dlr.de/113714/
Document Type:Thesis (Master's)
Title:Optimierung eines neuronalen Netzes zur Objekterkennung unter Verwendung evolutionärer Algorithmen
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Kornfeld, Nilsnils.kornfeld (at) dlr.deUNSPECIFIED
Date:6 April 2017
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Number of Pages:92
Status:Published
Keywords:Neural Networks, Neuronale Netze, Objekterkennung, CNN, Machine Learning, Evolutionäre Algorithmen
Institution:Freie Universität Berlin
Department:Dahlem Center for Machine Learning and Robotics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - I.MoVe (old)
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Transportation Systems > Verkehrsdatenerfassung
Deposited By: Kornfeld, Nils
Deposited On:28 Aug 2017 15:39
Last Modified:23 Feb 2019 00:21

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.