A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2014/394828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850230224308928512 |
|---|---|
| author | Zhekang Dong Shukai Duan Xiaofang Hu Lidan Wang Hai Li |
| author_facet | Zhekang Dong Shukai Duan Xiaofang Hu Lidan Wang Hai Li |
| author_sort | Zhekang Dong |
| collection | DOAJ |
| description | In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme. |
| format | Article |
| id | doaj-art-210ad84467ca4e68b8e345603bfaaf3a |
| institution | OA Journals |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2014-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-210ad84467ca4e68b8e345603bfaaf3a2025-08-20T02:03:57ZengWileyThe Scientific World Journal2356-61401537-744X2014-01-01201410.1155/2014/394828394828A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID ControlZhekang Dong0Shukai Duan1Xiaofang Hu2Lidan Wang3Hai Li4School of Electronics and Information Engineering, Southwest University, Chongqing 400715, ChinaSchool of Electronics and Information Engineering, Southwest University, Chongqing 400715, ChinaDepartment of MBE, City University of Hong Kong, Hong KongSchool of Electronics and Information Engineering, Southwest University, Chongqing 400715, ChinaDepartment of ECE, University of Pittsburgh, Pittsburgh, PA 15261, USAIn this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.http://dx.doi.org/10.1155/2014/394828 |
| spellingShingle | Zhekang Dong Shukai Duan Xiaofang Hu Lidan Wang Hai Li A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control The Scientific World Journal |
| title | A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control |
| title_full | A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control |
| title_fullStr | A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control |
| title_full_unstemmed | A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control |
| title_short | A Novel Memristive Multilayer Feedforward Small-World Neural Network with Its Applications in PID Control |
| title_sort | novel memristive multilayer feedforward small world neural network with its applications in pid control |
| url | http://dx.doi.org/10.1155/2014/394828 |
| work_keys_str_mv | AT zhekangdong anovelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT shukaiduan anovelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT xiaofanghu anovelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT lidanwang anovelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT haili anovelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT zhekangdong novelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT shukaiduan novelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT xiaofanghu novelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT lidanwang novelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol AT haili novelmemristivemultilayerfeedforwardsmallworldneuralnetworkwithitsapplicationsinpidcontrol |