Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 1 de 1
Filtrar
Más filtros

Banco de datos
Tipo del documento
Asunto de la revista
Intervalo de año de publicación
1.
Neural Netw ; 177: 106389, 2024 Sep.
Artículo en Inglés | MEDLINE | ID: mdl-38788291

RESUMEN

In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices turn out to be a class of matrices which correspond to Hebbian kernels revised by a reiterated unlearning protocol. Remarkably, the extent of such unlearning is proved to be related to the regularization hyperparameter of the loss function and to the training time. Thus, we can design strategies to avoid overfitting that are formulated in terms of regularization and early-stopping tuning. The generalization capabilities of these attractor networks are also investigated: analytical results are obtained for random synthetic datasets, next, the emerging picture is corroborated by numerical experiments that highlight the existence of several regimes (i.e., overfitting, failure and success) as the dataset parameters are varied.


Asunto(s)
Aprendizaje Automático , Redes Neurales de la Computación , Algoritmos , Neuronas/fisiología , Humanos
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA