The Function Representation of Artificial Neural Network
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2019
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911412449705984 |
|---|---|
| author | Ma, Zhongkui |
| author_facet | Ma, Zhongkui |
| contents | This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be recognized that the current ANN can be placed in a more reasonable framework. Perhaps all questions about ANN will be eliminated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1908_10493 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | The Function Representation of Artificial Neural Network Ma, Zhongkui Machine Learning Functional Analysis This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be recognized that the current ANN can be placed in a more reasonable framework. Perhaps all questions about ANN will be eliminated. |
| title | The Function Representation of Artificial Neural Network |
| topic | Machine Learning Functional Analysis |
| url | https://arxiv.org/abs/1908.10493 |