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 the 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 18 |
Editors | Yingxu WANG, Sam KWONG, Jerome FELDMAN , Newton HOWARD, Phillip SHEU, Bernard WIDROW |
Publisher | IEEE |
Pages | 6-15 |
Number of pages | 10 |
ISBN (Electronic) | 9781538633601 |
ISBN (Print) | 9781538633618 |
DOIs | |
Publication status | Published - Jul 2018 |
Externally published | Yes |
Event | 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018 - Berkeley, United States Duration: 16 Jul 2018 → 18 Jul 2018 |
Conference
Conference | 17th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2018 |
---|---|
Country/Territory | United States |
City | Berkeley |
Period | 16/07/18 → 18/07/18 |
Keywords
- Analytic methodologies
- Applications
- Cognitive systems
- Deep NNs
- Denotational mathematics
- Language sequence learning
- Neural networks (NNs)
- Recurrent NNs
- Sequence learning
- Visual sequence learning