| Título |
Topology-based representative datasets to reduce neural network training resources |
| Autores |
Gonzalez-Diaz, Rocio , Gutierrez-Naranjo, Miguel A. , PALUZO HIDALGO, EDUARDO |
| Publicación externa |
Si |
| Medio |
NEURAL COMPUTING & APPLICATIONS |
| Alcance |
Article |
| Naturaleza |
Científica |
| Cuartil JCR |
2 |
| Cuartil SJR |
1 |
| Impacto JCR |
6 |
| Impacto SJR |
1.169 |
| Fecha de publicacion |
01/09/2022 |
| ISI |
000791074200004 |
| DOI |
10.1007/s00521-022-07252-y |
| Abstract |
One of the main drawbacks of the practical use of neural networks is the long time required in the training process. Such a training process consists of an iterative change of parameters trying to minimize a loss function. These changes are driven by a dataset, which can be seen as a set of labeled points in an n-dimensional space. In this paper, we explore the concept of a representative dataset which is a dataset smaller than the original one, satisfying a nearness condition independent of isometric transformations. Representativeness is measured using persistence diagrams (a computational topology tool) due to its computational efficiency. We theoretically prove that the accuracy of a perceptron evaluated on the original dataset coincides with the accuracy of the neural network evaluated on the representative dataset when the neural network architecture is a perceptron, the loss function is the mean squared error, and certain conditions on the representativeness of the dataset are imposed. These theoretical results accompanied by experimentation open a door to reducing the size of the dataset to gain time in the training process of any neural network. |
| Palabras clave |
Data reduction; Neural networks; Representative datasets; Computational topology |
| Miembros de la Universidad Loyola |
|
Gestionar cookies