TY - GEN
T1 - Data Driven Fuzzy and Neural Dynamic Systems Modeling
AU - Leite, Daniel
AU - Gomide, Fernando
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The paper addresses data driven fuzzy modeling and long-short term memory structures, and evaluate their performance in modeling nonlinear dynamic systems. These are representative and powerful modeling paradigms representative of the state of the art of fuzzy and deep neural modeling approaches. Models complexity and approximation capabilities are evaluated, and their usefulness is discussed in front of the predictions they produce. Overall, the results suggest that they are competitive with alternative methods such as convolutional and Gaussian process.
AB - The paper addresses data driven fuzzy modeling and long-short term memory structures, and evaluate their performance in modeling nonlinear dynamic systems. These are representative and powerful modeling paradigms representative of the state of the art of fuzzy and deep neural modeling approaches. Models complexity and approximation capabilities are evaluated, and their usefulness is discussed in front of the predictions they produce. Overall, the results suggest that they are competitive with alternative methods such as convolutional and Gaussian process.
KW - Dynamic Systems
KW - Fuzzy Modeling
KW - Recurrent Neural Networks
UR - https://www.scopus.com/pages/publications/85179839056
U2 - 10.1109/ICMLC58545.2023.10327983
DO - 10.1109/ICMLC58545.2023.10327983
M3 - Conference contribution
AN - SCOPUS:85179839056
T3 - Proceedings - International Conference on Machine Learning and Cybernetics
SP - 321
EP - 325
BT - Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
PB - IEEE Computer Society
T2 - 22nd International Conference on Machine Learning and Cybernetics, ICMLC 2023
Y2 - 9 July 2023 through 11 July 2023
ER -