scholarly journals On the stability of an adaptive learning dynamics in traffic games

2018 ◽  
Vol 5 (4) ◽  
pp. 265-282
Author(s):  
Miguel A. Dumett ◽  
◽  
Roberto Cominetti ◽  
Keyword(s):  
Adaptive Learning ◽  
Learning Dynamics ◽  
The Stability

scholarly journals Stability Analysis of Neural Networks-Based System Identification

2008 ◽  
Vol 2008 ◽  
pp. 1-8 ◽  
Author(s):  
Talel Korkobi ◽  
Mohamed Djemel ◽  
Mohamed Chtourou
Keyword(s):  
Stability Analysis ◽  
Adaptive Learning ◽  
Learning Rule ◽  
Stability Domain ◽  
Learning Rate ◽  
Training Algorithm ◽  
Adaptive Learning Rate ◽  
Systems Identification ◽  
The Stability ◽  
Convergence Stability

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.

Neural Network Adaptive Control of Free Floating Space Robot with Actuator Saturation

2014 ◽  
Vol 590 ◽  
pp. 380-385 ◽  
Author(s):  
Guo Liang Zhang ◽  
Ting Lei ◽  
Fan Yang ◽  
Zhuang Cai
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Control Strategy ◽  
Actuator Saturation ◽  
Space Robot ◽  
Global Approximation ◽  
Neural Network Approach ◽  
The Neural Network ◽  
On Line ◽  
The Stability

This paper proposes an adaptive neural network law for trajectory tracking of a class of free-floating space robot with actuator saturation. Using neural network with global approximation, the control strategy design an on-line real time adaptive learning law to approach the uncertain model and the actuator saturation nonlinearity. The neural network approach errors and outside disturbance can be eliminated by a robust controller.The control strategy need not depend on the model, and can be used under actuator saturation.The control strategy can guarantee the stability of system and the asymptotic convergence of tracking errors based on the Lyapunov’s theory. The simulation results indicate that the proposed strategy can effectively work with actuator saturation.

scholarly journals Adaptive Learning Based Tracking Control of Marine Vessels with Prescribed Performance

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Zhao Xu ◽  
Shuzhi Sam Ge ◽  
Changhua Hu ◽  
Jinwen Hu
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Tracking Control ◽  
Tracking Error ◽  
Adaptive Tracking ◽  
Performance Constraints ◽  
Tracking Controller ◽  
Unknown Disturbances ◽  
The Stability ◽  
Marine Vessels

A novel adaptive tracking controller of fully actuated marine vessels is proposed with completely unknown dynamics and external disturbances. The model of dominant dynamic behaviors and unknown disturbances of the vessel are learned by a neural network in real time. The controller is designed and it unifies backstepping and adaptive neural network techniques with predefined tracking performance constraints on the tracking convergence rate and the transient and steady-state tracking error. The stability of the proposed adaptive tracking controller of the vessel is proven with a uniformly bounded tracking error. The proposed adaptive tracking controller is shown to be effective in the tracking control of marine vessels by simulations.

scholarly journals Economic Dynamics under Heterogeneous Adaptive Learning: General Criteria and Sufficient Conditions for Stability

2019 ◽  
Vol 19 (4) ◽  
pp. 87-103
Author(s):  
A. S. Bogomolova ◽  
D. V. Kolyuzhnov
Keyword(s):  
Adaptive Learning ◽  
Necessary Conditions ◽  
Learning Algorithm ◽  
Sufficient Conditions ◽  
Dsge Models ◽  
Shock Process ◽  
Sufficient And Necessary Conditions ◽  
Process Behavior ◽  
The Stability ◽  
Sign Conditions

The article extends the results of Honkapohja and Mitra (2006) and Kolyuzhnov (2011) and provides criteria and sufficient conditions for stability in a structurally heterogeneous economy under heterogeneous adaptive learning of agents. The criteria for stability under heterogeneous mixed RLS/SG learning for four classes of models – without lags and with lags of the endogenous variable and with t or t – 1 – dating of expectations – and sufficient conditions for stability for the cases of the diagonal structure of the shock process behavior or the heterogeneous RLS learning are presented in terms of the corresponding Jacobian matrices. In addition, the study presents a very useful criterion for the stability for all types of models under mixed RLS/SG learning with equal degrees of inertia for each type of learning algorithm in terms of stability of a suitably defined average economy with two agents. The derived criteria and sufficient conditions for stability are based on the results of the theory of stochastic approximation and are presented in terms of mixture of structural and learning heterogeneity, which are essential to get sufficient and necessary conditions for stability irrespective of heterogeneity in learning presented in terms of E-stability of suitably defined aggregate economies, the “same sign” conditions and the E-stability of a suitably defined average economy and its subeconomies. The fundamental nature of the approach adopted in the paper makes it possible to apply the results to a vast majority of the existing and prospective linear and linearized economic models (including estimated DSGE models) with adaptive learning of agents.

Learning Control of Robot Manipulators

1993 ◽  
Vol 115 (2B) ◽  
pp. 402-411 ◽  
Author(s):  
Roberto Horowitz
Keyword(s):  
Adaptive Learning ◽  
Robot Manipulators ◽  
Learning Control ◽  
Integral Transforms ◽  
Stability And Convergence ◽  
Control Algorithms ◽  
Convergence Properties ◽  
Motor Dexterity ◽  
The Stability ◽  
Learning Schemes

Learning control encompasses a class of control algorithms for programmable machines such as robots which attain, through an iterative process, the motor dexterity that enables the machine to execute complex tasks. In this paper we discuss the use of function identification and adaptive control algorithms in learning controllers for robot manipulators. In particular, we discuss the similarities and differences between betterment learning schemes, repetitive controllers and adaptive learning schemes based on integral transforms. The stability and convergence properties of adaptive learning algorithms based on integral transforms are highlighted and experimental results illustrating some of these properties are presented.

scholarly journals REAL-TIME, ADAPTIVE LEARNING VIA PARAMETERIZED EXPECTATIONS

2013 ◽  
Vol 19 (2) ◽  
pp. 245-269 ◽  
Author(s):  
Michele Berardi ◽  
John Duffy
Keyword(s):  
Steady State ◽  
Nonlinear System ◽  
Real Time ◽  
Euler Equations ◽  
Adaptive Learning ◽  
Learning Dynamics ◽  
Expected Values ◽  
Nonlinear Learning

We explore real-time adaptive nonlinear learning dynamics in stochastic macroeconomic systems. Rather than linearizing nonlinear Euler equations where expectations play a role around a steady state, we instead approximate the nonlinear expected values using the method of parameterized expectations. Further, we assume that these approximated expectations are updated in real time as new data become available. We argue that this method of real-time parameterized expectations learning provides a plausible alternative to real-time adaptive learning dynamics under linearized versions of the same nonlinear system, and we provide a comparison of the two approaches.

REPLICATOR DYNAMIC LEARNING IN MUTH'S MODEL OF PRICE MOVEMENTS

2012 ◽  
Vol 18 (3) ◽  
pp. 573-592 ◽  
Author(s):  
Eran A. Guse ◽  
Joel Carton
Keyword(s):  
Adaptive Learning ◽  
Production Level ◽  
Stability Conditions ◽  
Stable States ◽  
Dynamic Learning ◽  
Replicator Dynamic ◽  
Stability Properties ◽  
Price Movements ◽  
The Stability

We investigate the stability properties of Muth's model of price movements when agents choose a production level using replicator dynamic learning. It turns out that when there is a discrete set of possible production levels, possible stable states and stability conditions differ between adaptive learning and replicator dynamic learning.

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

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.

Open discussion

1982 ◽  
Vol 99 ◽  
pp. 605-613
Author(s):  
P. S. Conti
Keyword(s):  
Buenos Aires ◽  
Large Mass ◽  
List Type ◽  
Common Phenomenon ◽  
Open Discussion ◽  
The Stability ◽  
Ring Nebulae

Conti: One of the main conclusions of the Wolf-Rayet symposium in Buenos Aires was that Wolf-Rayet stars are evolutionary products of massive objects. Some questions:–Do hot helium-rich stars, that are not Wolf-Rayet stars, exist?–What about the stability of helium rich stars of large mass? We know a helium rich star of ∼40 MO. Has the stability something to do with the wind?–Ring nebulae and bubbles : this seems to be a much more common phenomenon than we thought of some years age.–What is the origin of the subtypes? This is important to find a possible matching of scenarios to subtypes.

Sign in / Sign up

Export Citation Format

Share Document