Skip to content
RDL
Network
Ecosystem
Switch app
TR
About
FAQ
Sign in
Get started
A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting — Kun Zhou (2024) | RDL Network
Back
Cite
Save
Save for later
Share
Home
Publications
A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting
Shared by
Witold Pedrycz
University of Alberta
A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting
Article
2024
en
Authors
+2 more
KZ
Kun Zhou
SO
Sung‐Kwun Oh
Witold Pedrycz
University of Alberta
Discussion
(0)
Sign in
to like and join the discussion.
No comments yet. Be the first to comment.
Related publications
Article
2024
Design of Hierarchical Neural Networks Using Deep LSTM and Self-Organizing Dynamical Fuzzy-Neural Network Architecture
Kun Zhou
,
Sung‐Kwun Oh
,
Jianlong Qiu
,
Witold Pedrycz
,
Kisung Seo
,
Jin Hee Yoon
Article
2021
Building Trend Fuzzy Granulation-Based LSTM Recurrent Neural Network for Long-Term Time-Series Forecasting
Yuqing Tang
,
Fusheng Yu
,
Witold Pedrycz
,
Xiyang Yang
,
Jiayin Wang
,
Shihu Liu
Article
2024
Oriented to a multi-learning mode: Establishing trend-fuzzy-granule-based LSTM neural networks for time series forecasting
Yuqing Tang
,
Fusheng Yu
,
Witold Pedrycz
,
Fang Li
,
Chenxi Ouyang
Article
2023
Traffic Prediction Method for Time Series Networks Based on ARIMA-LSTM Model
Tianhao Hou
,
Hongyan Xing
,
Xinyi Liang
Article
2025
A Hybrid Optimized Long-Term Time Series Forecasting Framework Via Dynamic Trend-Based Information Granulation
Mingli Song
,
Qingyu Wang
,
Witold Pedrycz
Discussion(0)
No comments yet. Be the first to comment.