Repository logo
 

Automated deep learning architecture design using differentiable architecture search (DARTS)

Simple item page
dc.contributor.authorSharma, Kartikay, author
dc.contributor.authorAnderson, Chuck, advisor
dc.contributor.authorBeveridge, Ross, committee member
dc.contributor.authorKirby, Michael, committee member
dc.date.accessioned2020-01-13T16:42:13Z
dc.date.available2020-01-13T16:42:13Z
dc.date.issued2019
dc.description.abstractCreating neural networks by hand is a slow trial-and-error based process. Designing new architectures similar to GoogleNet or FractalNets, which use repeated tree-based structures, is highly likely to be inefficient and sub-optimal because of the large number of possibilities for composing such structures. Recently, neural architecture search algorithms have been able to automate the process of architecture design and have often attained state-of-the-art performances on CIFAR-10, ImageNet and Penn Tree Bank datasets. Even though the search time has been reduced to tens of GPU hours from tens of thousands of GPU hours, most search algorithms rely on additional controllers and hypernetworks to generate architecture encoding or predict weights for sampled architectures. These controllers and hypernetworks might require optimal structure when deployed on a new task on a new dataset. And since this is done by hand, the problem of architecture search is not really solved. Differentiable Architecture Search (DARTS) avoids this problem by using gradient descent methods. In this work, the DARTS algorithm is studied under various conditions and search hyperparameters. DARTS is applied to CIFAR-10 to check reproducibility of the original results. It is also tested in a new setting — on the CheXpert dataset — to discover new architectures and is compared to a baseline DenseNet121 model. The architectures searched using DARTS achieve better performance on the validation set than the baseline model.
dc.format.mediumborn digital
dc.format.mediummasters theses
dc.identifierSharma_colostate_0053N_15836.pdf
dc.identifier.urihttps://hdl.handle.net/10217/199856
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartof2000-2019
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectconvolutional neural networks (CNNs)
dc.subjectdifferentiable architecture search
dc.subjectCheXpert dataset
dc.subjectneural architecture search
dc.subjectDARTS
dc.titleAutomated deep learning architecture design using differentiable architecture search (DARTS)
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineComputer Science
thesis.degree.grantorColorado State University
thesis.degree.levelMasters
thesis.degree.nameMaster of Science (M.S.)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sharma_colostate_0053N_15836.pdf
Size:
1.48 MB
Format:
Adobe Portable Document Format
Download

Collections

2000-2019
Theses and Dissertations