Efficient Implementation of Multilayer Perceptrons: Reducing Execution Time and Memory Consumption

A technique is presented that reduces the required memory of neural networks through improving weight storage. In contrast to traditional methods, which have an exponential memory overhead with the increase in network size, the proposed method stores only the number of connections between neurons. T...

Descripció completa

Dades bibliogràfiques

Autors principals:	Francisco Cedron, Sara Alvarez-Gonzalez, Ana Ribas-Rodriguez, Santiago Rodriguez-Yañez, Ana Belen Porto-Pazos
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2024-09-01
Col·lecció:	Applied Sciences
Matèries:	neural networks multilayer perceptron compressed weight matrix weight density sparsity
Accés en línia:	https://www.mdpi.com/2076-3417/14/17/8020
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!