In this paper we propose a particular class of multilayer perceptrons, which describes possibly non-linear phenomena, linked with Lukasiewicz logic; we show how we can name a neural network with a formula and, viceversa, how we can associate a class of neural networks to each formula. Moreover, we introduce the definition of Lukasiewicz Equivalent Neural Networks to stress the strong connection between different neural networks via Lukasiewicz logical objects.
Lukasiewicz equivalent neural networks
DI NOLA, Antonio;LENZI, Giacomo;VITALE, GAETANO
2016
Abstract
In this paper we propose a particular class of multilayer perceptrons, which describes possibly non-linear phenomena, linked with Lukasiewicz logic; we show how we can name a neural network with a formula and, viceversa, how we can associate a class of neural networks to each formula. Moreover, we introduce the definition of Lukasiewicz Equivalent Neural Networks to stress the strong connection between different neural networks via Lukasiewicz logical objects.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.