The Resource KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula
KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula
Resource Information
The item KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula represents a specific, individual, material embodiment of a distinct intellectual or artistic creation found in University of Missouri-Kansas City Libraries.This item is available to borrow from all library branches.
Resource Information
The item KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula represents a specific, individual, material embodiment of a distinct intellectual or artistic creation found in University of Missouri-Kansas City Libraries.
This item is available to borrow from all library branches.
- Summary
- Deep Learning (DL) has received considerable attention from the AI community. However, we suffer from the lack of ability in interpretation and annotation of the outcomes from extensive and exhausting learning efforts. In this thesis, we propose an automatic metadata extraction both from DL models as well as their publications and populate ontologies in Deep Learning. The automatically populated ontology represents the state-of-the-art (SOTA) results in Deep Learning based on the metadata extracted from models (model name, accuracy, network models, output, parameters) as well as ones from publications (paper title, author, topics, images, tables, data source). The evaluation of the ontology has been conducted with the models and publications from the SOTA research publications. Studying and understanding deep learning models is the base step for any deep learning engineer and availability of many deep learning frameworks makes it difficult for a developer to understand the model implementation and to study it deeply. In addition, users have to deal with huge computational requirements of the Machine Learning world and have to invest a lot of time in analyzing the model based on every parameter. It is even more tough to find the right data to replicate or evaluate the model, as data pre-processing is a crucial step in getting the right model. To handle these situations, in this thesis, we have developed an approach to extract possible information from a research paper, link it to datasets, tag the pre- trained models and built a deep learning knowledge base out of it. We have further used Natural Language Processing techniques such as Lemmatization, POS tagging, Named Entity Recognition to process the filtered data from research articles/papers and obtain Triplet <Subject, Predicate, Object> format. These triplets are used to validate the extracted meta data and use to fill in any missing data. The application links a Model -> Source Code -> Research Paper, which has great potential in understanding the models based on their framework. We have created a web application where users can upload models/documentation, view existing models from the created knowledge base, categorize the models based on framework, language, the class name. The application also visualizes the model and its architecture in detail and also presents the user with pre-trained models (if existing). We have extracted images, tables, topics, categories, datasets and pre-trained models from various sources and linked these details to a publication. In this way, the application and its knowledge base present a system for users to host, find, compare, study and analyze the deep learning models, which help the developers in understanding the model's behavior. Using this we can also find model similarities based on architecture and this also gives scope for building a recommendation system for the future
- Language
- eng
- Extent
- 1 online resource (66 pages)
- Note
-
- "A thesis in Computer Science."
- Advisor: Yugyung Lee
- Vita
- Contents
-
- Introduction
- Background and related work
- Proposed work
- results and evaluation
- Conclusion and future work
- Label
- KB4DL : building a knowledge base for deep learning
- Title
- KB4DL
- Title remainder
- building a knowledge base for deep learning
- Statement of responsibility
- by Ruthvic Punyamurtula
- Title variation
- Building a knowledge base for deep learning
- Language
- eng
- Summary
- Deep Learning (DL) has received considerable attention from the AI community. However, we suffer from the lack of ability in interpretation and annotation of the outcomes from extensive and exhausting learning efforts. In this thesis, we propose an automatic metadata extraction both from DL models as well as their publications and populate ontologies in Deep Learning. The automatically populated ontology represents the state-of-the-art (SOTA) results in Deep Learning based on the metadata extracted from models (model name, accuracy, network models, output, parameters) as well as ones from publications (paper title, author, topics, images, tables, data source). The evaluation of the ontology has been conducted with the models and publications from the SOTA research publications. Studying and understanding deep learning models is the base step for any deep learning engineer and availability of many deep learning frameworks makes it difficult for a developer to understand the model implementation and to study it deeply. In addition, users have to deal with huge computational requirements of the Machine Learning world and have to invest a lot of time in analyzing the model based on every parameter. It is even more tough to find the right data to replicate or evaluate the model, as data pre-processing is a crucial step in getting the right model. To handle these situations, in this thesis, we have developed an approach to extract possible information from a research paper, link it to datasets, tag the pre- trained models and built a deep learning knowledge base out of it. We have further used Natural Language Processing techniques such as Lemmatization, POS tagging, Named Entity Recognition to process the filtered data from research articles/papers and obtain Triplet <Subject, Predicate, Object> format. These triplets are used to validate the extracted meta data and use to fill in any missing data. The application links a Model -> Source Code -> Research Paper, which has great potential in understanding the models based on their framework. We have created a web application where users can upload models/documentation, view existing models from the created knowledge base, categorize the models based on framework, language, the class name. The application also visualizes the model and its architecture in detail and also presents the user with pre-trained models (if existing). We have extracted images, tables, topics, categories, datasets and pre-trained models from various sources and linked these details to a publication. In this way, the application and its knowledge base present a system for users to host, find, compare, study and analyze the deep learning models, which help the developers in understanding the model's behavior. Using this we can also find model similarities based on architecture and this also gives scope for building a recommendation system for the future
- Cataloging source
- UMK
- http://library.link/vocab/creatorName
- Punyamurtula, Ruthvic
- Degree
- M.S.
- Dissertation note
- (School of Computing and Engineering).
- Dissertation year
- 2019.
- Granting institution
- University of Missouri-Kansas City,
- Illustrations
- illustrations
- Index
- no index present
- Literary form
- non fiction
- Nature of contents
-
- dictionaries
- bibliography
- theses
- http://library.link/vocab/relatedWorkOrContributorDate
- 1960-
- http://library.link/vocab/relatedWorkOrContributorName
- Lee, Yugyung
- http://library.link/vocab/subjectName
-
- Machine learning
- Metadata
- Data mining
- Label
- KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula
- Note
-
- "A thesis in Computer Science."
- Advisor: Yugyung Lee
- Vita
- Antecedent source
- not applicable
- Bibliography note
- Includes bibliographical references (pages 61-65)
- Carrier category
- online resource
- Carrier category code
-
- cr
- Carrier MARC source
- rdacarrier
- Color
- black and white
- Content category
- text
- Content type code
-
- txt
- Content type MARC source
- rdacontent
- Contents
- Introduction -- Background and related work -- Proposed work -- results and evaluation -- Conclusion and future work
- Control code
- 1104844519
- Dimensions
- unknown
- Extent
- 1 online resource (66 pages)
- File format
- one file format
- Form of item
- online
- Level of compression
- mixed
- Media category
- computer
- Media MARC source
- rdamedia
- Media type code
-
- c
- Other physical details
- illustrations.
- Quality assurance targets
- not applicable
- Specific material designation
- remote
- System control number
- (OCoLC)1104844519
- System details
-
- The full text of the thesis is available as an Adobe Acrobat .pdf file; Adobe Acrobat Reader required to view the file
- Mode of access: World Wide Web
- Label
- KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula
- Note
-
- "A thesis in Computer Science."
- Advisor: Yugyung Lee
- Vita
- Antecedent source
- not applicable
- Bibliography note
- Includes bibliographical references (pages 61-65)
- Carrier category
- online resource
- Carrier category code
-
- cr
- Carrier MARC source
- rdacarrier
- Color
- black and white
- Content category
- text
- Content type code
-
- txt
- Content type MARC source
- rdacontent
- Contents
- Introduction -- Background and related work -- Proposed work -- results and evaluation -- Conclusion and future work
- Control code
- 1104844519
- Dimensions
- unknown
- Extent
- 1 online resource (66 pages)
- File format
- one file format
- Form of item
- online
- Level of compression
- mixed
- Media category
- computer
- Media MARC source
- rdamedia
- Media type code
-
- c
- Other physical details
- illustrations.
- Quality assurance targets
- not applicable
- Specific material designation
- remote
- System control number
- (OCoLC)1104844519
- System details
-
- The full text of the thesis is available as an Adobe Acrobat .pdf file; Adobe Acrobat Reader required to view the file
- Mode of access: World Wide Web
Library Locations
Library Links
Embed
Settings
Select options that apply then copy and paste the RDF/HTML data fragment to include in your application
Embed this data in a secure (HTTPS) page:
Layout options:
Include data citation:
<div class="citation" vocab="http://schema.org/"><i class="fa fa-external-link-square fa-fw"></i> Data from <span resource="http://link.library.umkc.edu/portal/KB4DL--building-a-knowledge-base-for-deep/F_CS3BfVU6A/" typeof="Book http://bibfra.me/vocab/lite/Item"><span property="name http://bibfra.me/vocab/lite/label"><a href="http://link.library.umkc.edu/portal/KB4DL--building-a-knowledge-base-for-deep/F_CS3BfVU6A/">KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula</a></span> - <span property="potentialAction" typeOf="OrganizeAction"><span property="agent" typeof="LibrarySystem http://library.link/vocab/LibrarySystem" resource="http://link.library.umkc.edu/"><span property="name http://bibfra.me/vocab/lite/label"><a property="url" href="http://link.library.umkc.edu/">University of Missouri-Kansas City Libraries</a></span></span></span></span></div>
Note: Adjust the width and height settings defined in the RDF/HTML code fragment to best match your requirements
Preview
Cite Data - Experimental
Data Citation of the Item KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula
Copy and paste the following RDF/HTML data fragment to cite this resource
<div class="citation" vocab="http://schema.org/"><i class="fa fa-external-link-square fa-fw"></i> Data from <span resource="http://link.library.umkc.edu/portal/KB4DL--building-a-knowledge-base-for-deep/F_CS3BfVU6A/" typeof="Book http://bibfra.me/vocab/lite/Item"><span property="name http://bibfra.me/vocab/lite/label"><a href="http://link.library.umkc.edu/portal/KB4DL--building-a-knowledge-base-for-deep/F_CS3BfVU6A/">KB4DL : building a knowledge base for deep learning, by Ruthvic Punyamurtula</a></span> - <span property="potentialAction" typeOf="OrganizeAction"><span property="agent" typeof="LibrarySystem http://library.link/vocab/LibrarySystem" resource="http://link.library.umkc.edu/"><span property="name http://bibfra.me/vocab/lite/label"><a property="url" href="http://link.library.umkc.edu/">University of Missouri-Kansas City Libraries</a></span></span></span></span></div>
