Optimization-based learning with bounded error for feedforward neural networks

被引：16

作者：

Alessandri, A ^{[1
]}

Sanguineti, M

Maggiore, M

机构：

[1] Natl Res Council Italy, Naval Automat Inst, IAN CNR, I-16149 Genoa, Italy

[2] Univ Genoa, DIST, Dept Commun Comp & Syst Sci, I-16145 Genoa, Italy

[3] Univ Toronto, Dept Elect & Comp Engn, Toronto, ON M5S 3G4, Canada

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2002年 / 13卷 / 02期

关键词：

feedforward neural networks; learning algorithms; nonlinear programming; optimization;

D O I：

10.1109/72.991413

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An optimization-based learning algorithm for feedforward neural networks is presented, in which the network weights are determined by minimizing a sliding-window cost. The algorithm is particularly well suited for batch learning and allows one to deal with large data sets in a computationally efficient way. An analysis of its convergence and robustness properties is made. Simulation results confirm the effectiveness of the algorithm and its advantages over learning based on backpropagation and extended Kalman filter.

引用

页码：261 / 273

页数：13

共 50 条

[1] OPTIMIZATION-BASED NEURAL NETWORKS COMPRESSION
Tahiri, Younes
Seddik, Mohamed El Amine
Tamaazousti, Mohamed
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 3512 - 3516
[2] Learning as a multi - Objective optimization in feedforward neural networks
Dumitras, A
Lazarescu, V
Negoita, M
[J]. FIRST INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ELECTRONIC SYSTEMS, PROCEEDINGS 1997 - KES '97, VOLS 1 AND 2, 1997, : 588 - 593
[3] Parallel Learning of Feedforward Neural Networks Without Error Backpropagation
Bilski, Jaroslaw
Wilamowski, Bogdan M.
[J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2016, 2016, 9692 : 57 - 69
[4] Optimization of feedforward neural networks
Han, J
Moraga, C
Sinne, S
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 1996, 9 (02) : 109 - 119
[5] Feedforward neural networks initialization based on discriminant learning
Chumachenko, Kateryna
Iosifidis, Alexandros
Gabbouj, Moncef
[J]. NEURAL NETWORKS, 2022, 146 : 220 - 229
[6] Optimization-Based Design of Bounded-Error Estimators Robust to Missing Data
Rutledge, Kwesi J.
Yong, Sze Zheng
Ozay, Necmiye
[J]. IFAC PAPERSONLINE, 2018, 51 (16): : 157 - 162
[7] Bounded error modeling using interval neural networks with parameter optimization
Guan, Shouping
Yu, Xiaoyu
[J]. NEUROCOMPUTING, 2022, 502 : 84 - 97
[8] Feedforward Error Learning Deep Neural Networks for Multivariate Deterministic Power Forecasting
Ko, Min-Seung
Lee, Kwangsuk
Hur, Kyeon
[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (09) : 6214 - 6223
[9] A fast and robust recursive prediction error learning algorithm for feedforward neural networks
Zhang, YM
Li, XR
[J]. PROCEEDINGS OF THE 35TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1996, : 2036 - 2041
[10] A fast learning algorithm of feedforward neural networks by using novel error functions
Jiang, MH
Deng, BX
Gielen, G
Tang, XF
Ruan, QQ
Yuan, BZ
[J]. 2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1171 - 1174

← 1 2 3 4 5 →