A Survey and Formal Analyses on Sequence Learning Methodologies and Deep Neural Networks
Wang Y., Leung H., Gavrilova M., Zatarain O., Graves D., Lu J., Howard N., Kwong S., Sheu P., Patel S.
© 2018 IEEE. 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.