1The City University of Hong Kong, Kowloon Tong, Hong Kong, China. eeleungc@cityu.edu.hk
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
We introduce a local Extended Kalman Filtering (EKF) training-pruning method for recurrent neural networks (RNNs). This approach reduces computational cost and storage, making RNNs more practical for real-world online applications.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: