A Survey and Analysis on Sequence Learning Methodologies and Deep Neural Networks
Patel, S., Wang, Y, Zatarain, O, Graves, D, Gavrilova, M and Howard, N (2018). A Survey and Analysis on Sequence Learning Methodologies and Deep Neural Networks. IEEE International Conferenece on Cognitive Informatics & Cognitive Computing. Berkeley, California, USA 16 - 18 Jul 2018 IEEE.
|Authors||Patel, S., Wang, Y, Zatarain, O, Graves, D, Gavrilova, M and Howard, N|
Sequence learning is one of the hard challenges to current machine learning 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||Sequence learning; neural networks; deep neural networks; recurrent neural networks; analytic methodologies; denotational mathematics; cognitive systems; visual sequence learning; language sequence learning|
|Accepted author manuscript|
CC BY 4.0
File Access Level
|16 Jul 2018|
|Publication process dates|
|Deposited||10 Jul 2018|
|Accepted||01 Jun 2018|
4views this month
3downloads this month