Designing stable neural identifier based on Lyapunov method
Authors
Abstract:
The stability of learning rate in neural network identifiers and controllers is one of the challenging issues which attracts great interest from researchers of neural networks. This paper suggests adaptive gradient descent algorithm with stable learning laws for modified dynamic neural network (MDNN) and studies the stability of this algorithm. Also, stable learning algorithm for parameters of MDNN is proposed. By proposed method, some constraints are obtained for learning rate. Lyapunov stability theory is applied to study the stability of the proposed algorithm. The Lyapunov stability theory is guaranteed the stability of the learning algorithm. In the proposed method, the learning rate can be calculated online and will provide an adaptive learning rare for the MDNN structure. Simulation results are given to validate the results.
similar resources
designing stable neural identifier based on lyapunov method
the stability of learning rate in neural network identifiers and controllers is one of the challenging issues which attracts great interest from researchers of neural networks. this paper suggests adaptive gradient descent algorithm with stable learning laws for modified dynamic neural network (mdnn) and studies the stability of this algorithm. also, stable learning algorithm for parameters of ...
full textdesigning unmanned aerial vehicle based on neuro-fuzzy systems
در این پایان نامه، کنترل نرو-فازی در پرنده هدایت پذیر از دور (پهپاد) استفاده شده است ابتدا در روش پیشنهادی اول، کنترل کننده نرو-فازی توسط مجموعه اطلاعات یک کنترل کننده pid به صورت off-line آموزش دیده است و در روش دوم یک کنترل کننده نرو-فازی on-line مبتنی بر شناسایی سیستم توسط شبکه عصبی rbf پیشنهاد شده است. سپس کاربرد این کنترل کننده در پهپاد بررسی شده است و مقایسه ای ما بین کنترل کننده های معمو...
An online adaptive PSS based on RBF neural network identifier
The design of a conventional power system stabilizer (PSS) based on linearized model cannot guarantee its performance in practical operating, so some intelligent techniques have been used. However, the parameters cannot update online in most of these mehods, thus the performance cannot be further improved. This paper adopts the design method of adaptive neural-fuzzy based power system stabilize...
full textPower Swings Damping Improvement with STATCOM and SMES Based on the Direct Lyapunov Method
In this paper a comprehensive approach is presented to improve power swings damping based on direct Lyapunov method. The approach combines superconducting magnetic energy storage (SMES) system with static synchronous compensator (STATCOM). Considering the energy absorption/injection ability of SMES, in transient states the combination exchanges both active and reactive powers with power system....
full textIdentifier Inference through Neural Networks
Source code can be treated similar as corpus constructed by natural language (Hindle et al., 2012). In this paper, we use the neural network model to study identifer naming convention problem. We find that neural network model can predict 16.5% identifiers correctly on a randomlyselected source file by training on the unrelated projects. In addition, we compare the performance of model on chara...
full textA Higher Order Online Lyapunov-Based Emotional Learning for Rough-Neural Identifiers
o enhance the performances of rough-neural networks (R-NNs) in the system identification, on the base of emotional learning, a new stable learning algorithm is developed for them. This algorithm facilitates the error convergence by increasing the memory depth of R-NNs. To this end, an emotional signal as a linear combination of identification error and its differences is used to achie...
full textMy Resources
Journal title
volume 3 issue 2
pages 141- 147
publication date 2015-10-01
By following a journal you will be notified via email when a new issue of this journal is published.
Hosted on Doprax cloud platform doprax.com
copyright © 2015-2023