A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks

Yingxu Wang; Henry Leung; Marina Gavrilova; Omar Zatarain; Daniel Graves; Jianhua Lu; Newton Howard; Sam Kwong; Phillip Sheu; Shushma Patel

doi:10.1109/ICCI-CC.2018.8482022

A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks

Yingxu Wang^*, Henry Leung, Marina Gavrilova, Omar Zatarain, Daniel Graves, Jianhua Lu, Newton Howard, Sam Kwong, Phillip Sheu, Shushma Patel

^*Corresponding author for this work

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

10 Citations (Scopus)

Abstract

Sequence learning is one of the hard challenges to current machine learning technologies and deep neural network technologies. This paper presents a literature survey and analysis on a variety of neural networks towards sequence learning. The conceptual models, methodologies, mathematical models and usages of classic neural networks and their learning capabilities are contrasted. Advantages and disadvantages of neural networks for sequence learning are formally analyzed. The state-of-the-art, theoretical problems and technical constraints of existing methodologies are reviewed. The needs for understanding temporal sequences by unsupervised or intensive-training-free learning theories and technologies are elaborated.

Original language	English
Title of host publication	Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018
Editors	Y. Wang, S. Kwong, J. Feldman, N. Howard, P. Sheu, B. Widrow
Publisher	IEEE
Pages	6-15
ISBN (Electronic)	9781538633601
DOIs	https://doi.org/10.1109/ICCI-CC.2018.8482022
Publication status	Published - Jul 2018
Event	17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018 - Berkeley, United States Duration: 16 Jul 2018 → 18 Jul 2018 https://www.ucalgary.ca/icci_cc/iccicc-18

Publication series

Name	IEEE International Conference on Cognitive Informatics
Publisher	IEEE

Conference

Conference	17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018
Place	United States
City	Berkeley
Period	16/07/18 → 18/07/18
Internet address	https://www.ucalgary.ca/icci_cc/iccicc-18

Research Keywords

Analytic methodologies
Applications
Cognitive systems
Deep NNs
Denotational mathematics
Language sequence learning
Neural networks (NNs)
Recurrent NNs
Sequence learning
Visual sequence learning

Access Output

10.1109/ICCI-CC.2018.8482022

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Wang, Y., Leung, H., Gavrilova, M., Zatarain, O., Graves, D., Lu, J., Howard, N., Kwong, S., Sheu, P., & Patel, S. (2018). A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks. In Y. Wang, S. Kwong, J. Feldman, N. Howard, P. Sheu, & B. Widrow (Eds.), Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018 (pp. 6-15). Article 8482022 (IEEE International Conference on Cognitive Informatics). IEEE. https://doi.org/10.1109/ICCI-CC.2018.8482022

Wang, Yingxu ; Leung, Henry ; Gavrilova, Marina et al. / A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks. Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018. editor / Y. Wang ; S. Kwong ; J. Feldman ; N. Howard ; P. Sheu ; B. Widrow. IEEE, 2018. pp. 6-15 (IEEE International Conference on Cognitive Informatics).

@inproceedings{870efa2f919e4b8895cd56c919f7c72d,

title = "A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks",

abstract = "Sequence learning is one of the hard challenges to current machine learning technologies and deep neural network technologies. This paper presents a literature survey and analysis on a variety of neural networks towards sequence learning. The conceptual models, methodologies, mathematical models and usages of classic neural networks and their learning capabilities are contrasted. Advantages and disadvantages of neural networks for sequence learning are formally analyzed. The state-of-the-art, theoretical problems and technical constraints of existing methodologies are reviewed. The needs for understanding temporal sequences by unsupervised or intensive-training-free learning theories and technologies are elaborated.",

keywords = "Analytic methodologies, Applications, Cognitive systems, Deep NNs, Denotational mathematics, Language sequence learning, Neural networks (NNs), Recurrent NNs, Sequence learning, Visual sequence learning",

author = "Yingxu Wang and Henry Leung and Marina Gavrilova and Omar Zatarain and Daniel Graves and Jianhua Lu and Newton Howard and Sam Kwong and Phillip Sheu and Shushma Patel",

year = "2018",

month = jul,

doi = "10.1109/ICCI-CC.2018.8482022",

language = "English",

series = "IEEE International Conference on Cognitive Informatics",

publisher = "IEEE",

pages = "6--15",

editor = "Y. Wang and S. Kwong and J. Feldman and N. Howard and P. Sheu and B. Widrow",

booktitle = "Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018",

address = "United States",

note = "17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018 ; Conference date: 16-07-2018 Through 18-07-2018",

url = "https://www.ucalgary.ca/icci_cc/iccicc-18",

}

Wang, Y, Leung, H, Gavrilova, M, Zatarain, O, Graves, D, Lu, J, Howard, N, Kwong, S, Sheu, P & Patel, S 2018, A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks. in Y Wang, S Kwong, J Feldman, N Howard, P Sheu & B Widrow (eds), Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018., 8482022, IEEE International Conference on Cognitive Informatics, IEEE, pp. 6-15, 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018, Berkeley, California, United States, 16/07/18. https://doi.org/10.1109/ICCI-CC.2018.8482022

A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks. / Wang, Yingxu; Leung, Henry; Gavrilova, Marina et al.
Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018. ed. / Y. Wang; S. Kwong; J. Feldman; N. Howard; P. Sheu; B. Widrow. IEEE, 2018. p. 6-15 8482022 (IEEE International Conference on Cognitive Informatics).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks

AU - Wang, Yingxu

AU - Leung, Henry

AU - Gavrilova, Marina

AU - Zatarain, Omar

AU - Graves, Daniel

AU - Lu, Jianhua

AU - Howard, Newton

AU - Kwong, Sam

AU - Sheu, Phillip

AU - Patel, Shushma

PY - 2018/7

Y1 - 2018/7

N2 - Sequence learning is one of the hard challenges to current machine learning technologies and deep neural network technologies. This paper presents a literature survey and analysis on a variety of neural networks towards sequence learning. The conceptual models, methodologies, mathematical models and usages of classic neural networks and their learning capabilities are contrasted. Advantages and disadvantages of neural networks for sequence learning are formally analyzed. The state-of-the-art, theoretical problems and technical constraints of existing methodologies are reviewed. The needs for understanding temporal sequences by unsupervised or intensive-training-free learning theories and technologies are elaborated.

AB - Sequence learning is one of the hard challenges to current machine learning technologies and deep neural network technologies. This paper presents a literature survey and analysis on a variety of neural networks towards sequence learning. The conceptual models, methodologies, mathematical models and usages of classic neural networks and their learning capabilities are contrasted. Advantages and disadvantages of neural networks for sequence learning are formally analyzed. The state-of-the-art, theoretical problems and technical constraints of existing methodologies are reviewed. The needs for understanding temporal sequences by unsupervised or intensive-training-free learning theories and technologies are elaborated.

KW - Analytic methodologies

KW - Applications

KW - Cognitive systems

KW - Deep NNs

KW - Denotational mathematics

KW - Language sequence learning

KW - Neural networks (NNs)

KW - Recurrent NNs

KW - Sequence learning

KW - Visual sequence learning

UR - http://www.scopus.com/inward/record.url?scp=85056475856&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85056475856&origin=recordpage

U2 - 10.1109/ICCI-CC.2018.8482022

DO - 10.1109/ICCI-CC.2018.8482022

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - IEEE International Conference on Cognitive Informatics

SP - 6

EP - 15

BT - Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018

A2 - Wang, Y.

A2 - Kwong, S.

A2 - Feldman, J.

A2 - Howard, N.

A2 - Sheu, P.

A2 - Widrow, B.

PB - IEEE

T2 - 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018

Y2 - 16 July 2018 through 18 July 2018

ER -

Wang Y, Leung H, Gavrilova M, Zatarain O, Graves D, Lu J et al. A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks. In Wang Y, Kwong S, Feldman J, Howard N, Sheu P, Widrow B, editors, Proceedings of 2018 IEEE 17th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018. IEEE. 2018. p. 6-15. 8482022. (IEEE International Conference on Cognitive Informatics). doi: 10.1109/ICCI-CC.2018.8482022

A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this