Implementing artificial neural networks through bionic construction.
It is evident through biology research that, biological neural network could be implemented through two means: by congenital heredity, or by posteriority learning. However, traditionally, artificial neural network, especially the Deep learning Neural Networks (DNNs) are implemented only through exha...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0212368 |
| _version_ | 1818588986132660224 |
|---|---|
| author | Hu He Xu Yang Zhiheng Xu Ning Deng Yingjie Shang Guo Liu Mengyao Ji Wenhao Zheng Jinfeng Zhao Liya Dong |
| author_facet | Hu He Xu Yang Zhiheng Xu Ning Deng Yingjie Shang Guo Liu Mengyao Ji Wenhao Zheng Jinfeng Zhao Liya Dong |
| author_sort | Hu He |
| collection | DOAJ |
| description | It is evident through biology research that, biological neural network could be implemented through two means: by congenital heredity, or by posteriority learning. However, traditionally, artificial neural network, especially the Deep learning Neural Networks (DNNs) are implemented only through exhaustive training and learning. Fixed structure is built, and then parameters are trained through huge amount of data. In this way, there are a lot of redundancies in the implemented artificial neural network. This redundancy not only requires more effort to train the network, but also costs more computing resources when used. In this paper, we proposed a bionic way to implement artificial neural network through construction rather than training and learning. The hierarchy of the neural network is designed according to analysis of the required functionality, and then module design is carried out to form each hierarchy. We choose the Drosophila's visual neural network as a test case to verify our method's validation. The results show that the bionic artificial neural network built through our method could work as a bionic compound eye, which can achieve the detection of the object and their movement, and the results are better on some properties, compared with the Drosophila's biological compound eyes. |
| first_indexed | 2024-12-16T09:33:28Z |
| format | Article |
| id | doaj.art-6d83aa948ad54bbc82a2079fd0413d3f |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-16T09:33:28Z |
| publishDate | 2019-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-6d83aa948ad54bbc82a2079fd0413d3f2022-12-21T22:36:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032019-01-01142e021236810.1371/journal.pone.0212368Implementing artificial neural networks through bionic construction.Hu HeXu YangZhiheng XuNing DengYingjie ShangGuo LiuMengyao JiWenhao ZhengJinfeng ZhaoLiya DongIt is evident through biology research that, biological neural network could be implemented through two means: by congenital heredity, or by posteriority learning. However, traditionally, artificial neural network, especially the Deep learning Neural Networks (DNNs) are implemented only through exhaustive training and learning. Fixed structure is built, and then parameters are trained through huge amount of data. In this way, there are a lot of redundancies in the implemented artificial neural network. This redundancy not only requires more effort to train the network, but also costs more computing resources when used. In this paper, we proposed a bionic way to implement artificial neural network through construction rather than training and learning. The hierarchy of the neural network is designed according to analysis of the required functionality, and then module design is carried out to form each hierarchy. We choose the Drosophila's visual neural network as a test case to verify our method's validation. The results show that the bionic artificial neural network built through our method could work as a bionic compound eye, which can achieve the detection of the object and their movement, and the results are better on some properties, compared with the Drosophila's biological compound eyes.https://doi.org/10.1371/journal.pone.0212368 |
| spellingShingle | Hu He Xu Yang Zhiheng Xu Ning Deng Yingjie Shang Guo Liu Mengyao Ji Wenhao Zheng Jinfeng Zhao Liya Dong Implementing artificial neural networks through bionic construction. PLoS ONE |
| title | Implementing artificial neural networks through bionic construction. |
| title_full | Implementing artificial neural networks through bionic construction. |
| title_fullStr | Implementing artificial neural networks through bionic construction. |
| title_full_unstemmed | Implementing artificial neural networks through bionic construction. |
| title_short | Implementing artificial neural networks through bionic construction. |
| title_sort | implementing artificial neural networks through bionic construction |
| url | https://doi.org/10.1371/journal.pone.0212368 |
| work_keys_str_mv | AT huhe implementingartificialneuralnetworksthroughbionicconstruction AT xuyang implementingartificialneuralnetworksthroughbionicconstruction AT zhihengxu implementingartificialneuralnetworksthroughbionicconstruction AT ningdeng implementingartificialneuralnetworksthroughbionicconstruction AT yingjieshang implementingartificialneuralnetworksthroughbionicconstruction AT guoliu implementingartificialneuralnetworksthroughbionicconstruction AT mengyaoji implementingartificialneuralnetworksthroughbionicconstruction AT wenhaozheng implementingartificialneuralnetworksthroughbionicconstruction AT jinfengzhao implementingartificialneuralnetworksthroughbionicconstruction AT liyadong implementingartificialneuralnetworksthroughbionicconstruction |