Deep learning using genetic algorithms

Show simple item record

dc.contributor.advisor Gaborski, Roger en_US
dc.contributor.author Lamos-Sweeney, Joshua
dc.date.accessioned 2012-08-15T17:10:18Z
dc.date.available 2012-08-15T17:10:18Z
dc.date.issued 2012
dc.identifier.uri http://hdl.handle.net/1850/15270
dc.description.abstract Deep Learning networks are a new type of neural network that discovers important object features. These networks determine features without supervision, and are adept at learning high level abstractions about their data sets. These networks are useful for a variety of tasks, but are difficult to train. This difficulty is compounded when multiple networks are trained in a layered fashion, which results in increased solution complexity as well as increased training time. This paper examines the use of Genetic Algorithms as a training mechanism for Deep Learning networks, with emphasis on training networks with a large number of layers, each of which is trained independently to reduce the computational burden and increase the overall flexibility of the algorithm. This paper covers the implementation of a multilayer deep learning network using a genetic algorithm, including tuning the genetic algorithm, as well as results of experiments involving data compression and object classification. This paper aims to show that a genetic algorithm can be used to train a non trivial deep learning network in place of existing methodologies for network training, and that the features extracted can be used for a variety of real world computational problems.
dc.language.iso en_US
dc.subject Deep learning en_US
dc.subject Genetic algorithms en_US
dc.subject.lcc QA76.87 .L36 2012
dc.subject.lcsh Neural networks (Computer science)
dc.subject.lcsh Genetic algorithms
dc.subject.lcsh Machine learning
dc.title Deep learning using genetic algorithms
dc.type Thesis
dc.description.college B. Thomas Golisano College of Computing and Information Sciences
dc.description.department Department of Computer Science

Files in this item

Files Size Format View
JLamos-SweeneyThesis5-17-2012.pdf 445.5Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse