An improved blind detection algorithm of chaos Hopfield neural network
In order to improve the flexibility of the activation function of the blind detection algorithm in Hopfield neural network,an activation function with better nonlinear approximation ability near the origin was proposed.For the case where the algorithm trapped in local optima,utilizing the good ergod...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2018-02-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018016/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530293976039424 |
|---|---|
| author | Dawei YU Shaowei CHEN Shujuan YU |
| author_facet | Dawei YU Shaowei CHEN Shujuan YU |
| author_sort | Dawei YU |
| collection | DOAJ |
| description | In order to improve the flexibility of the activation function of the blind detection algorithm in Hopfield neural network,an activation function with better nonlinear approximation ability near the origin was proposed.For the case where the algorithm trapped in local optima,utilizing the good ergodicity and randomness of chaos mapping,chaos was used to generate the initial sequence at the starting point of the algorithm,and small-amplitude chaotic perturbation was performed when the current global optimum value was constant,so as to reduce the error performance of the algorithm.The simulation results show that the proposed algorithm reduces the sensitivity of neurons to input values,has strong anti-interference ability and fast convergence speed,and improves the blind detection performance. |
| format | Article |
| id | doaj-art-6e3772dc4c564c1aa7a79e521bc6fd33 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2018-02-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-6e3772dc4c564c1aa7a79e521bc6fd332025-01-15T03:05:13ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012018-02-0134818759597044An improved blind detection algorithm of chaos Hopfield neural networkDawei YUShaowei CHENShujuan YUIn order to improve the flexibility of the activation function of the blind detection algorithm in Hopfield neural network,an activation function with better nonlinear approximation ability near the origin was proposed.For the case where the algorithm trapped in local optima,utilizing the good ergodicity and randomness of chaos mapping,chaos was used to generate the initial sequence at the starting point of the algorithm,and small-amplitude chaotic perturbation was performed when the current global optimum value was constant,so as to reduce the error performance of the algorithm.The simulation results show that the proposed algorithm reduces the sensitivity of neurons to input values,has strong anti-interference ability and fast convergence speed,and improves the blind detection performance.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018016/blind detectionchaos disturbanceHopfield neural networkactivation function |
| spellingShingle | Dawei YU Shaowei CHEN Shujuan YU An improved blind detection algorithm of chaos Hopfield neural network Dianxin kexue blind detection chaos disturbance Hopfield neural network activation function |
| title | An improved blind detection algorithm of chaos Hopfield neural network |
| title_full | An improved blind detection algorithm of chaos Hopfield neural network |
| title_fullStr | An improved blind detection algorithm of chaos Hopfield neural network |
| title_full_unstemmed | An improved blind detection algorithm of chaos Hopfield neural network |
| title_short | An improved blind detection algorithm of chaos Hopfield neural network |
| title_sort | improved blind detection algorithm of chaos hopfield neural network |
| topic | blind detection chaos disturbance Hopfield neural network activation function |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018016/ |
| work_keys_str_mv | AT daweiyu animprovedblinddetectionalgorithmofchaoshopfieldneuralnetwork AT shaoweichen animprovedblinddetectionalgorithmofchaoshopfieldneuralnetwork AT shujuanyu animprovedblinddetectionalgorithmofchaoshopfieldneuralnetwork AT daweiyu improvedblinddetectionalgorithmofchaoshopfieldneuralnetwork AT shaoweichen improvedblinddetectionalgorithmofchaoshopfieldneuralnetwork AT shujuanyu improvedblinddetectionalgorithmofchaoshopfieldneuralnetwork |