Mason Archival Repository Service

A Cross-Dataset Evaluation of Genetically Evolved Neural Network Architectures

Show simple item record

dc.contributor.advisor Domeniconi, Carlotta
dc.contributor.author Gelman, Ben
dc.creator Gelman, Ben
dc.date 2019-04-04
dc.date.accessioned 2019-07-01T20:22:34Z
dc.date.available 2019-07-01T20:22:34Z
dc.identifier.uri https://hdl.handle.net/1920/11479
dc.description.abstract The design of deep neural networks is often colloquially described as an `art.' Although there are some common, guiding principles such as using convolutions for data with spatial locality or using recurrence for data with temporal characteristics, neural network architectures tend to be manually engineered. Few works currently provide methods to determine optimal architectures and hyper parameters. In this work, we generate empirical evidence for neural network architecture choices. We use a genetic algorithm to evolve 980 neural networks for a variety of common data sets. We analyze the characteristics of the highest performing architectures, compare those traits across data sets, and present a set of generalizable neural network design patterns.
dc.language.iso en en_US
dc.subject neural networks en_US
dc.subject deep learning en_US
dc.subject genetic algorithms en_US
dc.subject data en_US
dc.title A Cross-Dataset Evaluation of Genetically Evolved Neural Network Architectures en_US
dc.type Thesis en_US
thesis.degree.name Master of Science in Computer Science en_US
thesis.degree.level Master's en_US
thesis.degree.discipline Computer Science en_US
thesis.degree.grantor George Mason University en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search MARS


Browse

My Account

Statistics