The Resource An evolutionary method for training autoencoders for Deep Learning Networks, by Sean Lander

An evolutionary method for training autoencoders for Deep Learning Networks, by Sean Lander

Label
An evolutionary method for training autoencoders for Deep Learning Networks
Title
An evolutionary method for training autoencoders for Deep Learning Networks
Statement of responsibility
by Sean Lander
Creator
Contributor
Author
Thesis advisor
Subject
Genre
Language
eng
Summary
Introduced in 2006, Deep Learning has made large strides in both supervised an unsupervised learning. The abilities of Deep Learning have been shown to beat both generic and highly specialized classification and clustering techniques with little change to the underlying concept of a multi-layer perceptron. Though this has caused a resurgence of interest in neural networks, many of the drawbacks and pitfalls of such systems have yet to be addressed after nearly 30 years: speed of training, local minima and manual testing of hyper-parameters. In this thesis we propose using an evolutionary technique in order to work toward solving these issues and increase the overall quality and abilities of Deep Learning Networks. In the evolution of a population of autoencoders for input reconstruction, we are able to abstract multiple features for each autoencoder in the form of hidden nodes, scoring the autoencoders based on their ability to reconstruct their input, and finally selecting autoencoders for crossover and mutation with hidden nodes as the chromosome. In this way we are able to not only quickly find optimal abstracted feature sets but also optimize the structure of the autoencoder to match the features being selected. This also allows us to experiment with different training methods in respect to data partitioning and selection, reducing overall training time drastically for large and complex datasets. This proposed method allows even large datasets to be trained quickly and efficiently with little manual parameter choice required by the user, leading to faster, more accurate creation of Deep Learning Networks
Cataloging source
MUU
http://library.link/vocab/creatorName
Lander, Sean
Degree
M.S.
Dissertation note
Thesis
Dissertation year
2014.
Government publication
government publication of a state province territory dependency etc
Granting institution
University of Missouri--Columbia
Illustrations
illustrations
Index
no index present
Literary form
non fiction
Nature of contents
  • dictionaries
  • bibliography
  • theses
http://library.link/vocab/relatedWorkOrContributorDate
1967-
http://library.link/vocab/relatedWorkOrContributorName
Shang, Yi
http://library.link/vocab/subjectName
  • Artificial intelligence
  • Neural networks (Computer science)
  • Genetic algorithms
Label
An evolutionary method for training autoencoders for Deep Learning Networks, by Sean Lander
Instantiates
Publication
Note
  • "MAY 2014."
  • "A Thesis Presented to The Faculty of the Graduate School At the University of Missouri--Columbia In Partial Fulfillment of the Requirements for the Degree Master of Science."
  • Advisor: Dr. Yi Shang
Accompanying material
2 supplementary files.
Bibliography note
Includes bibliographical references (page 35)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier.
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent.
Control code
917537949
Extent
1 online resource (vi, 35 pages)
Form of item
online
Media category
computer
Media MARC source
rdamedia.
Media type code
  • c
Other physical details
color illustrations +
Specific material designation
remote
System control number
(OCoLC)917537949
Label
An evolutionary method for training autoencoders for Deep Learning Networks, by Sean Lander
Publication
Note
  • "MAY 2014."
  • "A Thesis Presented to The Faculty of the Graduate School At the University of Missouri--Columbia In Partial Fulfillment of the Requirements for the Degree Master of Science."
  • Advisor: Dr. Yi Shang
Accompanying material
2 supplementary files.
Bibliography note
Includes bibliographical references (page 35)
Carrier category
online resource
Carrier category code
  • cr
Carrier MARC source
rdacarrier.
Content category
text
Content type code
  • txt
Content type MARC source
rdacontent.
Control code
917537949
Extent
1 online resource (vi, 35 pages)
Form of item
online
Media category
computer
Media MARC source
rdamedia.
Media type code
  • c
Other physical details
color illustrations +
Specific material designation
remote
System control number
(OCoLC)917537949

Library Locations

  • Health Sciences LibraryBorrow it
    2411 Holmes St, Kansas City, Kansas City, MO, 64108, US
    39.083418 -94.575323
  • LaBudde Special CollectionsBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Leon E. Bloch Law LibraryBorrow it
    500 E. 52nd Street, Kansas City, MO, 64110, US
    39.032488 -94.581967
  • Marr Sound ArchivesBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.034642 -94.576835
  • Miller Nichols LibraryBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
    39.035061 -94.576518
  • UMKCBorrow it
    800 E 51st St, Kansas City, MO, 64110, US
Processing Feedback ...