eprintid: 18553
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/85/53
datestamp: 2024-06-04 14:10:52
lastmod: 2024-06-04 14:10:52
status_changed: 2024-06-04 14:03:35
type: article
metadata_visibility: show
creators_name: Al-Selwi, S.M.
creators_name: Hassan, M.F.
creators_name: Abdulkadir, S.J.
creators_name: Muneer, A.
title: LSTM Inefficiency in Long-Term Dependencies Regression Problems
ispublished: pub
note: cited By 9
abstract: Recurrent neural networks (RNNs) are an excellent fit for regression problems where sequential data are the norm since their recurrent internal structure can analyse and process data for long. However, RNNs are prone to the phenomenal vanishing gradient problem (VGP) that causes the network to stop learning and generate poor prediction accuracy, especially in long-term dependencies. Originally, gated units such as long short-term memory (LSTM) and gated recurrent unit (GRU) were created to address this problem. However, VGP was and still is an unsolved problem, even in gated units. This problem occurs during the backpropagation process when the recurrent network weights tend to vanishingly reduce and hinder the network from learning the correlation between temporally distant events (long-term dependencies), that results in slow or no network convergence. This study aims to provide an empirical analysis of LSTM networks with an emphasis on inefficiency in long-term dependencies convergence because of VGP. Case studies on NASA�s turbofan engine degradation are examined and empirically analysed. © 2023, Penerbit Akademia Baru. All rights reserved.
date: 2023
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85163351348&doi=10.37934%2faraset.30.3.1631&partnerID=40&md5=1f0df50bc2794111a9911c966e2b12c3
id_number: 10.37934/araset.30.3.1631
full_text_status: none
publication: Journal of Advanced Research in Applied Sciences and Engineering Technology
volume: 30
number: 3
pagerange: 16-31
refereed: TRUE
citation:   Al-Selwi, S.M. and Hassan, M.F. and Abdulkadir, S.J. and Muneer, A.  (2023) LSTM Inefficiency in Long-Term Dependencies Regression Problems.  Journal of Advanced Research in Applied Sciences and Engineering Technology, 30 (3).  pp. 16-31.