Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks

Simple item page
dc.contributor.advisorPatel, Ankiten_US
dc.contributor.committeeMemberBaraniuk , Richarden_US
dc.creatorMichalenko, Joshua Jamesen_US
dc.date.accessioned2019-05-16T19:27:17Zen_US
dc.date.available2019-05-16T19:27:17Zen_US
dc.date.created2019-05en_US
dc.date.issued2019-04-19en_US
dc.date.submittedMay 2019en_US
dc.date.updated2019-05-16T19:27:17Zen_US
dc.description.abstractWe investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specially, we train a RNN on positive and negative examples from a regular language, and ask if there is a simple decoding function that maps states of this RNN to states of the minimal deterministic fnite automaton (MDFA) for the language. Our experiments show that such a decoding function indeed exists, and that it maps states of the RNN not to MDFA states, but to states of an abstraction obtained by clustering small sets of MDFA states into “superstates”. A framework for performing large scale systematic representation analysis between the two language models is discussed. Quantitative analysis surprisingly shows that linear decoding functions are suffcient for the task and an analysis of a range of abstraction functions is given. A qualitative analysis reveals new interpretations of how RNNs implement hierarchical priors during the language recognition task. Overall, the results suggest a strong structural relationship between internal representations used by RNNs and fnite automata, and explain the well-known ability of RNNs to recognize formal grammatical structure.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationMichalenko, Joshua James. "Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks." (2019) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/105421">https://hdl.handle.net/1911/105421</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/105421en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectLanguage recognitionen_US
dc.subjectRecurrent Neural Networksen_US
dc.subjectRepresentation Learningen_US
dc.subjectdeterministic finite automatonen_US
dc.subjectautomatonen_US
dc.titleRepresenting Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networksen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentElectrical and Computer Engineeringen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
MICHALENKO-DOCUMENT-2019.pdf
Size:
4.2 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.85 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations