Paper Info
Title
A PLS-based pruning algorithm for simplified long–short term memory neural network in time series prediction
Abstract
As an extensively used model for time series prediction, the Long–Short Term Memory (LSTM) neural network suffers from shortcomings such as high computational cost and large memory requirement, due to its complex structure. To address these problems, a PLS-based pruning algorithm is hereby proposed for a simplified LSTM (PSLSTM). First, a hybrid strategy is designed to simplify the internal structure of LSTM, which combines the structure simplification and parameter reduction for gates. Second, partial least squares (PLS) regression coefficients are used as the metric to evaluate the importance of the memory blocks, and the redundant hidden layer size is pruned by merging unimportant blocks with their most correlated ones. The Backpropagation Through Time (BPTT) algorithm is utilized as the learning algorithm to update the network parameters. Finally, several benchmark and practical datasets for time series prediction are used to evaluate the performance of the proposed PSLSTM. The experimental results demonstrate that the PLS-based pruning algorithm can achieve the trade-off between a good generalization ability and a compact network structure. The computational complexity is improved by the simple internal structure as well as the compact hidden layer size, without sacrificing prediction accuracy.
Year
DOI
Venue
2022
10.1016/j.knosys.2022.109608
Knowledge-Based Systems
Keywords
DocType
Volume
Long–short term memory (LSTM),Time series prediction,Internal structure simplification,Partial least squares (PLS) regression,Pruning algorithm,Hidden layer size
Journal
254
ISSN
Citations 
PageRank 
0950-7051
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Wenjing Li100.34
Xiaoxiao Wang200.34
Hong-Gui Han347639.06
Jun-Fei Qiao479874.56