Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909525072674816 |
|---|---|
| author | Kohler, Michael Krzyzak, Adam Sänger, Alisha |
| author_facet | Kohler, Michael Krzyzak, Adam Sänger, Alisha |
| contents | Image classification from independent and identically distributed random variables is considered. Image classifiers are defined which are based on a linear combination of deep convolutional networks with max-pooling layer. Here all the weights are learned by stochastic gradient descent. A general result is presented which shows that the image classifiers are able to approximate the best possible deep convolutional network. In case that the a posteriori probability satisfies a suitable hierarchical composition model it is shown that the corresponding deep convolutional neural network image classifier achieves a rate of convergence which is independent of the dimension of the images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07128 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization Kohler, Michael Krzyzak, Adam Sänger, Alisha Statistics Theory Image classification from independent and identically distributed random variables is considered. Image classifiers are defined which are based on a linear combination of deep convolutional networks with max-pooling layer. Here all the weights are learned by stochastic gradient descent. A general result is presented which shows that the image classifiers are able to approximate the best possible deep convolutional network. In case that the a posteriori probability satisfies a suitable hierarchical composition model it is shown that the corresponding deep convolutional neural network image classifier achieves a rate of convergence which is independent of the dimension of the images. |
| title | Learning of deep convolutional network image classifiers via stochastic gradient descent and over-parametrization |
| topic | Statistics Theory |
| url | https://arxiv.org/abs/2404.07128 |