This thesis introduces a novel neural network, the Extreme Long Short-Term Memory (E-LSTM), combine the advantages of Long Short-Term Memory (LSTM) networks and Extreme Learning Machines (ELM). Empirical evidence demonstrates that E-LSTM significantly bolsters computational efficiency, concurrently maintaining a high prediction accuracy.
History
Pagination
70 p.
Open access
Yes
Language
eng
Degree type
Master
Degree name
MEng
Copyright notice
All rights reserved
Editor/Contributor(s)
Sui Yang Khoo, Michael Norton
Faculty
Faculty of Science, Engineering and Built Environment