Stability Analysis of Neural Networks-Based System Identification

This paper treats some problems related to nonlinear systems identification. A stability analysis neural network model for identifying nonlinear dynamic systems is presented. A constrained adaptive stable backpropagation updating law is presented and used in the proposed identification approach. The proposed backpropagation training algorithm is modified to obtain an adaptive learning rate guarantying convergence stability. The proposed learning rule is the backpropagation algorithm under the condition that the learning rate belongs to a specified range defining the stability domain. Satisfying such condition, unstable phenomena during the learning process are avoided. A Lyapunov analysis leads to the computation of the expression of a convenient adaptive learning rate verifying the convergence stability criteria. Finally, the elaborated training algorithm is applied in several simulations. The results confirm the effectiveness of the CSBP algorithm.

Download Full-text

The Improved Training Algorithm of Deep Learning with Self-Adaptive Learning Rate

2018 18th International Symposium on Communications and Information Technologies (ISCIT) ◽

10.1109/iscit.2018.8587999 ◽

2018 ◽

Author(s):

Sutit Ongart ◽

Kietikul Jearanaitanakij ◽

Jirapat Sangthong

Keyword(s):

Deep Learning ◽

Adaptive Learning ◽

Learning Rate ◽

Training Algorithm ◽

Adaptive Learning Rate ◽

Self Adaptive

Download Full-text

A Neural Network Design Methodology for Structural Control

Volume 1C: 16th Biennial Conference on Mechanical Vibration and Noise ◽

10.1115/detc97/vib-3775 ◽

1997 ◽

Author(s):

S. M. Yang ◽

G. S. Lee

Keyword(s):

Neural Network ◽

Network Design ◽

Adaptive Learning ◽

Design Methodology ◽

Learning Rule ◽

Smart Structure ◽

Learning Rate ◽

Design Parameters ◽

Adaptive Learning Rate ◽

Propagation Network

Abstract One of the major difficulties in neural network applications is the selection of the parameters in network configuration and the coefficients in learning rule for fast convergence as well as best system performance. This paper developed a network design methodology so that the optimal design parameters/coefficients can be determined in a systematic way thereby avoiding the lengthy trial-and-error. The methodology combines the Taguchi method of quality engineering and the back-propagation network with an adaptive learning rate for their advantages in implementation feasibility and performance robustness. Vibration suppression experiments of a composite smart structure with embedded piezoelectric sensor/actuator validate that the methodology provides an efficient neural controller design, including the plant order, the number of hidden layer neurons, the number of training patterns, and the coefficients of adaptive learning rate.

Download Full-text

On-line neural training algorithm with sliding mode control and adaptive learning rate

Neurocomputing ◽

10.1016/j.neucom.2006.07.019 ◽

2007 ◽

Vol 70 (16-18) ◽

pp. 2687-2691 ◽

Cited By ~ 18

Author(s):

A. Nied ◽

S.I. Seleme ◽

G.G. Parma ◽

B.R. Menezes

Keyword(s):

Sliding Mode Control ◽

Adaptive Learning ◽

Sliding Mode ◽

Learning Rate ◽

Training Algorithm ◽

Mode Control ◽

Adaptive Learning Rate ◽

On Line

Download Full-text

The Improved Training Algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate

2009 International Conference on Computational Intelligence and Natural Computing ◽

10.1109/cinc.2009.111 ◽

2009 ◽

Cited By ~ 21

Author(s):

Yong Li ◽

Yang Fu ◽

Hui Li ◽

Si-Wen Zhang

Keyword(s):

Neural Network ◽

Adaptive Learning ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Learning Rate ◽

Training Algorithm ◽

Adaptive Learning Rate ◽

Self Adaptive

Download Full-text

Improving Adaptive Learning Rate With Backpropogation on Retail Rice Price Prediction in Traditional Markets

IJISTECH (International Journal Of Information System & Technology) ◽

10.30645/ijistech.v3i1.26 ◽

2019 ◽

Vol 3 (1) ◽

pp. 1

Author(s):

Erwin Binsar Hamonangan Ompusunggu ◽

Solikhun Solikhun ◽

Iin Parlina ◽

Sumarno Sumarno ◽

Indra Gunawan

Keyword(s):

Adaptive Learning ◽

Retail Price ◽

Learning Rate ◽

Traditional Markets ◽

Adaptive Learning Rate ◽

Architectural Models ◽

Rice Prices ◽

The Government ◽

The Stability ◽

Accuracy Data

Rice is the most important staple food and carbohydrate food in the world especially people in Indonesia. This study aims to predict the retail price of rice in traditional markets using backpropogation by improvising Adaptive Learning Rate to increase the value of accuracy. Data sources were obtained from the Central Statistics Agency (BPS) in 33 provinces in Indonesia for the retail price of rice in the traditional market (Rupiah / kg) for the past 6 years (2011-2016). The results of the study state that the improvised learning rate uses 2 models: 2-10-1 and 2-15-1 (LR= 0,1; 0,5; 0,9) that the best architectural models are 4-15-1 (LR= 0.9) with an accuracy of 82%, Training MSE 0,000999936, Testing MSE 0.016051433 and Epoch 20515. The results of this study are expected to provide input to the government in providing input on predictions of retail rice prices that have an impact on the stability of rice prices in Indonesia.

Download Full-text