A CONSTRUCTIVE BASED HYBRID TRAINING ALGORITHM FOR FEEDFORWARD NEURAL NETWORKS

被引：0

作者：

Ben Nasr, Mounir ^{[1
]}

Chtourou, Mohamed ^{[1
]}

机构：

[1] ENIS, Dept Elect Engn, Res Unit Intelligent Control Design & Optimizat C, Sfax 3038, Tunisia

来源：

2009 6TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS AND DEVICES, VOLS 1 AND 2 | 2009年

关键词：

Constructive algorithm; feedforward neural network; gradient descent method; supervised and unsupervised learning; incremental training; Fuzzy self-organizing feature map; Hybrid training; LEARNING RATE; CONVERGENCE;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a new learning algorithm for feedforward neural networks. This algorithm uses the vigilance parameter to generate the hidden layer neurons. This process improves the initial weight problem and the adaptive neurons of the hidden layer. The proposed approach is based on combined unsupervised and supervised learning. In this algorithm, the weights between input and hidden layers are firstly adjusted by Kohonen algorithm with fuzzy neighborhood, whereas the weights connecting hidden and output layers are adjusted using gradient descent method. Two simulation examples are provided to demonstrate the efficiency of the approach compared with a number of other methods.

引用

页码：97 / 100

页数：4

共 50 条

[1] A constructive algorithm for feedforward neural networks with incremental training
Liu, DR
Chang, TS
Zhang, Y
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2002, 49 (12) : 1876 - 1879
[2] A hybrid training algorithm for feedforward neural networks
Ben Nasr, Mounir
Chtourou, Mohamed
[J]. NEURAL PROCESSING LETTERS, 2006, 24 (02) : 107 - 117
[3] A Hybrid Training Algorithm for Feedforward Neural Networks
Mounir Ben Nasr
Mohamed Chtourou
[J]. Neural Processing Letters, 2006, 24 : 107 - 117
[4] A constructive algorithm for feedforward neural networks
Institute of System Science, East China Normal University
不详
不详
[J]. 1600, 659-664 (2004):
[5] A hybrid linear/nonlinear training algorithm for feedforward neural networks
McLoone, S
Brown, MD
Irwin, G
Lightbody, G
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (04): : 669 - 684
[6] Fault tolerant constructive algorithm for feedforward neural networks
Hammadi, NC
Ohmameuda, T
Kaneko, K
Ito, H
[J]. PACIFIC RIM INTERNATIONAL SYMPOSIUM ON FAULT-TOLERANT SYSTEMS, PROCEEDINGS, 1997, : 215 - 220
[7] ODE-LM: A hybrid training algorithm for feedforward neural networks
[J]. Zhang, L. (lzhang@xidian.edu.cn), 1600, Springer Verlag (215):
[8] Constructive training methods for feedforward neural networks with binary weights
Mayoraz, E
Aviolat, F
[J]. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1996, 7 (02) : 149 - 166
[9] Step acceleration based training algorithm for feedforward neural networks
Li, YL
Wang, KQ
Zhang, D
[J]. 16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2002, : 84 - 87
[10] Heterogeneous double populations based hybrid genetic algorithm design for training feedforward neural networks
Zhang, Li Feng
He, Rong
Yan, Meng Ling
[J]. 2012 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2012,

← 1 2 3 4 5 →