vp-rnn

KO | EN

gitlite — search

#python #react #llm #go #linux #docker #windows #awesome #kubernetes #awesome-list #pytorch #security #ios #open-source

(★ 11)

[TNNLS'19] Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications

vp-rnn 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications

## About
This repository contains the MATLAB implementation of <a href="https://ieeexplore.ieee.org/document/8589008">Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications</a> (VP-RNN).

# Varying-Parameter RNN
An RNN Model for Solving Time-Varying Control Problems

- [[Paper 1](https://ieeexplore.ieee.org/document/8589008)] (Convergence Analysis)

- [[Paper 2](https://ieeexplore.ieee.org/document/8463509)] (Robustness Analysis)

- [[Slide](https://github.com/ldkong1205/Varying-Parameter-RNN/blob/master/Slide(in%20Chinese).pdf)] (in Chinese)

INTRODUCTION
-----
Many practical control problems can be solved by being formulated as time-varying quadratic minimization and time-varying quadratic programing problems. In this project, a power-type varying-parameter recurrent neural network is proposed and analyzed to effectively solve the resulting time-varying problems, as well as the original practical problems. For a clear understanding, we introduce this model from three aspects: design, analysis, and applications. Specifically, the reason why and the method we use to design this neural network model for solving online TVQP problems subject to time-varying linear equality/inequality are described in detail. The theoretical analysis confirms that when activated by six commonly used activation functions, the proposed network achieves a superexponential convergence rate. In contrast to the traditional zeroing neural network with fixed design parameters, the proposed model has better convergence performance. Comparative simulations with state-of-the-art methods confirm the advantages. Furthermore, the application of the proposed to a robot motion planning problem verifies the feasibility, applicability, and efficiency.

Keywords: `time-varying systems`,  `recurrent neural networks`,  `convergence`, `robustness`, `dynamic programming`.

![image](https://github.com/ldkong1205/Varying-Parameter-RNN/blob/master/image/Kinova.jpg)

NETWORK STRUCTURE
-----

![image](https://github.com/ldkong1205/Varying-Parameter-RNN/blob/master/image/network.jpg)

LICENSE
-----

- Contact: ldkong@ieee.org.

Citation
-----

```
@ARTICLE{8589008, 
  author={Z. {Zhang} and L. {Kong} and L. {Zheng}}, 
  journal={IEEE Transactions on Neural Networks and Learning Systems}, 
  title={Power-Type Varying-Parameter RNN for Solving TVQP Problems: Design, Analysis, and Applications}, 
  year={2019}, 
  volume={30}, 
  number={8}, 
  pages={2419-2433}, 
}
```

```
@ARTICLE{8463509, 
  author={Z. {Zhang} and L. {Kong} and L. {Zheng} and P. {Zhang} and X. {Qu} and B. {Liao} and Z. {Yu}}, 
  journal={IEEE Transactions on Systems, Man, and Cybernetics: Systems}, 
  title={Robustness Analysis of a Power-Type Varying-Parameter Recurrent Neural Network for Solving Time-Varying QM and QP  Problems and Applications}, 
  year={2020}, 
  volume={50}, 
  number={12}, 
  pages={5106-5118}, 
}
```

vp-rnn

vp-rnn 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

vp-rnn

vp-rnn 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README